Blog

Congrats to the Kaggle Benchmarking Challenge Winners!

A few weeks ago we teamed up with Kaggle to ask a deceptively simple question: how do you actually...

Android 17 on a 4.9 Kernel: LineageOS 24.0 on the Pixel 3a

The Pixel 3a runs LineageOS 24.0, Android 17, on its original 4.9 kernel with SELinux enforcing and Google apps. One kernel fix, five platform forks and a set of device-tree changes, each traced to a line of a boot log.

Thank you to everyone who pointed out the phishing posts we got yesterday. We're working on improved mechanisms to automatically reject those types of attacks.

A post by Ben Halpern

Crows, Moths, and Makefiles: How 300 Megabytes of Crow DNA Explains Why a 20-Kilobyte Scar File Outsmarts a Terabyte LLM

Why do New Caledonian crows bend wire into hooks with zero training while a trillion-parameter LLM flies straight into the same production bug zapper? How Anthony Zador's Genomic Bottleneck explains what 'instinct' really is in AI coding agents.

Gemma 4 E2B in JAX on One TPU v5e: bf16 or 4-Bit, Python or Rust, and How It Stands Against vLLM

Gemma 4 E2B served three ways on one Cloud TPU v5e chip: a pure-JAX engine in Python, the same graph written in Rust and compiled by the libtpu that JAX loads, and vLLM, all timed by one client. bf16 beats 4-bit in the JAX engine, the Rust engine matches the JAX engine's tokens, and over HTTP it decodes at vLLM's rate with the fastest first token.

Join the Presage SmartSpectra SDK Challenge: $3,000 in Prizes Across 10 Winners!

We're excited to announce our newest challenge with Presage! The Presage SmartSpectra SDK Challenge...

Securing an Angular Firebase AI App with Email/Password Authentication (Part 3: Lightweight Home Screen, Lazy CDK Dialog, and Header Navigation)

We now have AuthService for authentication and SignInModalComponent for users to enter their email...

Prompt Pad: What Is Open Source?

Chances are you're already using open-source software without realizing it. In this episode of...

Welcome Thread - v400

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

Leveling the Playing Field: Building a 100% Offline Kubernetes Docs RAG Exam Assistant with Web AI, Gemma 4, and WebGPU

How to enable fair, zero-cost, air-gapped AI assistance in technical classrooms and...

That's a Wrap on Hacktoberfest 2026! 🎃👻

Hacktoberfest 2026 wrapped up on October 31st! Thank you to everyone who built, hosted, mentored,...

Let's see where you code!

I’ve been writing a lot about AWS lately, so let’s take a breather. This is my little corner of the...

Prompt Pad: Lock Your AI's Output Schema in Google AI Studio

If you've ever tried to parse an LLM response in code, you know the pain: the format changes slightly...

Gemma 4 in Rust on TorchTPU: A Native TPU Rig With PyO3 and MCP

Gemma 4 E2B with the model in Rust, served from a TPU v5e-1 VM through PyO3 and a C++ shim over ATen, with no tch and no pinned PyTorch, an OpenAI endpoint, an MCP server and a local chat UI.

Prompt Pad: Frame Your Persona for Better AI Answers

Want better answers from AI? Start by telling it who to be. In this episode of Prompt Pad,...

Gemma 4 in Rust on TorchTPU: Hands On With Colab

A Rust crate reads the checkpoint, runs all 35 layers of Gemma 4 E2B and drives the decode loop on one TPU v5e chip in Colab, with every operation a TorchTPU kernel and the same tokens as compiled Python.

Securing an Angular Firebase AI App with Email/Password Authentication (Part 1: Emulator, AuthService, and Route Guard) [GDE]

Anyone with the public URL can use my tokens to perform image analysis and text-to-speech, which can...

Singularity News :: CCG

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...

Giving AI Pain: The Architecture of Synthetic Scars & The Rapid-Regret Miner

Why 90% of AI coding frustration comes from the Quota vs. Prompt-Compliance Death Loop, why Rich Sutton's Bitter Lesson fails in open-world software, and how we compile mid-flight collisions into 4-Vector Synthetic Scars and a Six-Pillar Critic.

Welcome to the Prompt Pad: AI Tips & Tricks with Rosendo Pili

Keeping up with AI is a full-time job. Prompt Pad is here to help you keep up a little at a...

AI Dev Weekly #32: GPT-6.1 Terra, Gemini Carbon, Kimi K3.1 and Copilot Fusion

Week of Oct 23-29: GPT-6.1 Terra, restricted Gemini Carbon access, Kimi K3.1 Pro, Copilot Fusion and GitHub's agentic workflow launches.

Performance vs Quality: Gemma 4 E2B Quantization on an NVIDIA L4 and a Tesla T4

Gemma 4 E2B from BF16 to Q2_K, speed against GSM8K accuracy, on an AWS L4 with byte-identical GGUF files and the same llama.cpp build as the Tesla T4. The L4 decodes 1.25 to 1.89 times faster, Q5_K_M is still the best trade, and switching GPUs changes nearly as many grades as quantizing from BF16 to Q5_K_M.

Gemini 4 Carbon Is #1 on AA Index — Still Fairwind-Only: Cyber Benches, $2/$10 $4/$20, and What to Do Before the API

Google DeepMind’s Gemini 4 Carbon (Oct 28) claims AA Index v5.0 #1 at 59 and SOTA cyber benches — still Fairwind/cyber-defenders first, no public model ID. Intro $2/$10 → $4/$20, 95% cache off, builder checklist before the API.

Accuracy vs Speed: Gemma 4 E2B Quantization Tradeoffs, BF16 to Q2_K

Gemma 4 E2B quantized from BF16 to Q2_K on one Tesla T4, every rung asked the same 250 GSM8K questions, and each answer buried at the rung where it first goes wrong. Q5_K_M and above hold the score; Q3_K_M loses 38; Q2_K gets 3 right. With thinking on, Q3_K_M wins back 17.

Welcome Thread - v399

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

Your Laptop Might Replace Most of Your AI Bill

I've never run an AI model on my own machine, and I assumed the cloud was the best way to get good...

Your DEV posts have a beautiful new share card ✨

The image that shows up when you share a DEV post just got a brand-new look! I got to work on...

Size Your Model to Where You Run It: Gemma 4 E2B and E4B on an AWS L4 and Two Small GPUs

A 24 GB NVIDIA L4 serves Gemma 4 E2B and E4B at only 1.2-1.3x an 8 GB desktop RTX 3050 for one user, with the same answers, because a 4-bit small model uses 13-29% of the card. Pick the model for the hardware, and the hardware for the model.

Join the Hacktoberfest Open-Source AI Challenge: Ghost in the Machine! $2,850 in Prizes Across 21 Winners.

Week 4 of our Hacktoberfest DEV Challenges starts today, and it's our final challenge of the series!...

Why bloc.add(...) Isn't What You Think: Synchronous Event Fast-Paths and 0ms Form Bindings

Why classic BLoC's StreamController forces an asynchronous microtask tax, how BlocSignal executes synchronous event handlers inline on the exact same call stack, and why this is the only way to build 120 FPS Generative UI form bindings.

🐾 DEV Pet Corner #3: Show Us Your Pets!

TL;DR DEV Pet Corner is back for another Sunday! It's a weekly series where we take a little break...

Let It Die: The Lazy Email Agent on TabPFN, Gemma and Temporal

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

Congrats to the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Winners!

We're excited to announce the winners of the Hacktoberfest Open-Source AI Challenge Week 2: Side...

Comic Studio AI: Turning Voice & Text Prompts into 4-Panel Comics with Google AI Studio, Gemini & Imagen

This post is my submission for DEV Education Track: Build Apps with Google AI Studio. ...

Building a Multimodal, Suggestion-Based AI Writing Coach with Gemini and Google Docs

When we use generative AI to proofread our daily writing—whether technical reports, business...

926 Steps, Two Lobotomies, and Zero Nudges: Flight-Testing the Commitment Machine Across Gemini, Claude, and GPT-OSS

A 2026 Harvard study of 718 companies found that AI agents write 30% more code and close zero additional tickets because review times jump 49%. Here is what happened when I put my 1986 Commitment Machine into live production across Gemini, Claude, and GPT-OSS.

Scaling stateful Gemini 4 Argon agent sessions on GKE: Connection draining, startup boost, and session persistence

Architect GKE for long-running Gemini 4 Argon agent sessions using VPA CPU startup boost, GCPBackendPolicy connection draining, and session checkpointing.

Congrats to the Sanity Challenge Winners!

We are thrilled to announce the winners of the Sanity Challenge, our partnership with Sanity built...

Building a Cross-Model Collaborative Workflow with Google Antigravity

Orchestrating Multiple AI Agents in Parallel via Custom Skills Series 1/2: Multi-Model...

Don't Be a Proxy Between Me and Your AI

I've had this conversation more times than I'd like to admit. I raise a technical question in a...

Multi-tier model routing on GKE: balancing Gemini 4 Argon reasoning depth with latency and cost

Build a high-throughput model routing gateway on GKE to dynamically route requests between Gemini 4 Argon, Gemini 3.8 Flash, and local Gemma 4 models.

I Got Tired of Coming into my Lab to Check the Pressure of my Cryocooler so I Built a Tool to do it for Me

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...

SlothSRE (NapOps): An Overnight Gemma 4 & ADK Agent That Compresses 418 Lines of 3 AM Alerts into a 2-Line Morning Digest

How I built a local-first open-weights Gemma 4, Google ADK, and Sentry Agent Tracing pipeline that deduplicates overnight stack traces, verifies git patches in a local pytest sandbox, and lets on-call engineers sleep until 8 AM.

Welcome Thread - v 398

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

Generative UI Without the Async Tax: Introducing bloc_signals_genui 1.0

Why we built a pure-Dart, 0ms synchronous Generative UI state machine on top of Google's official A2UI protocol—supporting two-way reactive forms, Riverpod/BLoC interop, Flutter Material 3, and ANSI terminal TUIs.

Can a 26B MoE Run on an 8 GB GPU? Gemma 4 26B A4B on an RTX 3050

Gemma 4 26B A4B, a 14.4 GB mixture-of-experts model, serves from an 8 GB RTX 3050 with most of its experts in system RAM: 131,072 tokens of context, 28 to 34 tok/s empty, and GSM8K and BFCL scores level with the 12B.

Stress-Testing Gemini 4 Argon: Building a 3D Flutter Kart Game in 15 Prompts with Zero Assets

Most AI coding benchmarks test standard web apps or CRUD dashboards. Frontier models can already...

Promise Delivered: Welcome to the DEV Hall of Fame (65 Authors, 65 Masterpieces)

Status: Promise delivered ✅ The Doors Are Open A little over a month ago, I published...

Dev Opportunity Radar #21: $500K Y Combinator Funding, Bolt Builders Week, and AI Safety Research Residency

TL;DR Welcome back to Dev Opportunity Radar! This is a weekly series where I share opportunities,...

Do Drafters Work on Small Models? Gemma 4 E2B and E4B on Two Small GPUs

Yes. Speculative decoding with Google's 59 MB QAT multi-token prediction (MTP) drafters speeds up Gemma 4 E4B 1.72x and E2B 1.40x on an 8 GB RTX 3050, and 1.49x and 1.18x on a 4 GB laptop GTX 1650 Ti, served by llama.cpp one request at a time, with unchanged GSM8K and BFCL scores.

Don't Assume Your Cloud T4 Runs at Spec: Gemma 4 Decode Falls 7% as the Card Warms

The same Tesla T4 on the same Google Cloud VM decoded Gemma 4 E2B at 115 tokens/s at 45 °C and 107 at 77 °C. The card sits at its 70 W limit, a hotter chip draws more power at the same clock, so the clock drops. No thermal throttle fires, and no spec sheet mentions it.

[AI in Practice] Upgrading from Gemini 3.5/3.6 to Gemini 4 Argon: Migration Notes and Pitfalls for LINE Bot Developers

Background I have a LINE Bot that I use every day, linebot-helper-python. I use it daily...

Building ora-tui with Google Antigravity & Gemini 4 Argon: An MS-DOS Retro TUI & OpenTelemetry Exporter for Oracle RAC, DB & SAN Multipath

How I pair-programmed with Google Antigravity powered by Gemini 4 Argon to build a zero-dependency Go TUI and OpenTelemetry/Prometheus observability stack for Oracle Databases and Linux SAN storage.

Natural Languages Have Design Trade-offs Too: Georgian Is Dynamically Typed, English Is Statically Typed

Table of Contents How This Started Feature #1: Articles (or the Lack of Them) The...

DuckLess: serverless DuckDB on Google Cloud, in your own project

Serverless DuckDB on Google Cloud, in your own project. Files on GCS, tables in BigQuery (read and write), what I measured, and what I learned.

Local image generation with llamadart for the Llama Village storybook

Beyond chat with llamadart · Part 4 Dash missed it. Pip’s scarf is by the pond, and all he has is...

Your AI Agent Just Got a Passport: Agent Identity on Google Cloud and the Redeploy Trap Nobody Talks About

Why your agents need their own identity Most teams run every AI agent under one shared...

Cómo construí ora-tui: Un gestor en consola (TUI) en Go sin dependencias para Oracle RAC y Single Instance

Descubre cómo diseñar una interfaz TUI en Go con marcos Unicode (┌─┐ / ╔═╗), auto-descubrimiento de clusters Oracle RAC y flujos de mantenimiento guiados por flechas sin depender de Oracle Instant Client.

Gemma 4 on a Used 8 GB RTX 3050: 116 Tokens/s for One User, 618 for 64

Gemma 4 E2B and E4B on a used RTX 3050 OEM in an old desktop, step by step: single-user speed, the full 131k context, concurrency, answer quality, and how it compares on price with laptop GPUs, ARM laptops, a T4 and a TPU v5e.

Requests, Promises, Assertions, and Declarations: Rewriting Our AI Agent Workflow as a 1986 'Committed Speech' Machine

Why do 200-line agent prompts, Asimov's Three Laws, and sequential pre-landing checklists all fail the same way? How Fernando Flores's 1986 Committed Speech, Nuel Belnap's 1977 4-Valued Logic, and Tony Hoare's 1978 CSP turned our Makefile and init.d workflow into a self-healing Commitment Machine.

Building Better Agents through End-to-End Evals

Deeply understand the task at hand The biggest mistake teams make with agents is...

Memory Isn’t Learning: Why AI Agents Keep Making the Same Mistakes

Have you ever told your AI agent something important, only to realize a few conversations later that...

Nobody’s winning the AI race yet

By Ryan Swift Yesterday, Google finally released its Gemini 4 Argon model for public use. It’s...

Are You Smarter Than a Fruit Fly?

Google mapped the complete male fruit fly brain, and my first question to an agent was “Can this run...

The Model Is the Easy Part

We spent the past few months on a question that sounds simple: what does it actually take to move a...

Design for Churn

The biggest design shift of the AI era isn’t about who writes the code. It’s about how long the code...

How I Feel about the Grace Hopper Celebration Getting Cancelled

The Grace Hopper Celebration has been around since 1994, and for a lot of people, it's the event for...

Join the Hacktoberfest Open-Source AI Challenge: Side Hustle! $2,550 in Prizes Across 18 Winners.

Week 2 of our five Hacktoberfest DEV Challenges starts today! Running through October 18, the...

Local embeddings with llamadart: how llamas share secrets

Beyond chat with llamadart · Part 2 Llama Village, where five llamas share a world without sharing...

Safe Autonomy in Kubernetes: Building AI Troubleshooting Agents with Google Cloud and Human-in-the-Loop Controls

Kubernetes troubleshooting often requires engineers to correlate pod events, container logs, resource...

If You Never Do Anything Else to Fix Your Prompts, Do This One Thing

Why do LLMs confidently invent APIs that have never existed in the history of the universe? It is not a memory defect. Agents hallucinated because they were committed to the prompt—and Fernando Flores solved the root cause in 1986.

THE UNHEARD: A Game That Sends You Outside, Teaches a Machine to Listen, and Makes It Prove Every Word

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

One Weekend: 3,000 Open-Source AI Projects

Every October for the past twelve years, developers around the world have taken part in...

ROI That Survives the Second Question

Judgment is the scarce resource in a world where intelligence is becoming a commodity. A business can...

Your Guide to AI Engineer New York 2026

AI Engineer New York is here! This conference built for Wall Street. Banking, hedge funds, fintech,...

Banks Are Renting Their Agents. These Two Built One.

Most banks aren't building their own agents. They're renting them. Bank Director's 2026 Technology...

Does your agent have ID?

Last month, an AI agent in Denmark booked a coffee tasting and paid for it. Danske Bank and...

Where to Spend Your Week at AI Engineer New York

AI Engineer New York has 137 sessions on the schedule and up to five running at any given moment....

What LLMs 'Know' That You Don't Know They Know: Stop Inventing Prompt DSLs and Ride 50 Years of Unix Pre-Training Gravity

Why did a 1976 Makefile (Part 3.6) and a 1983 Unix init.d directory (Part 3.7) outperform 2,000 lines of English prompt rules? Because prompt engineering is static symbol linkage against 50 years of pre-trained computer science canon.

Congrats to the Hacktoberfest Weekend Challenge: Build for a Friend Winners!

We are so excited to announce the winners of the Hacktoberfest Weekend Challenge: Build for a Friend,...

Congrats to Our First MLH x DEV Writing Challenge Winner!

We just wrapped the very first month of the MLH x DEV Writing Challenge, our new way of celebrating...

Dev Opportunity Radar #20: $2M AI Reasoning Challenge, PayPal AI Hackathon, and Coinbase Analytics Challenge

TL;DR Welcome back to Dev Opportunity Radar. This is a weekly series where I share opportunities,...

Gemma 4 From E2B to 31B on an AMD MI300X: fp8 Overtakes bf16 From 12B Up

Every Gemma 4 size from E2B to 31B served on one AMD Instinct MI300X in bf16, fp8, int8 W8A8 and int4 W4A16, on the same vLLM image. fp8 goes from 0.75x bf16 for one request at E2B to 1.23x at 31B and is faster than bf16 in every cell at 12B and 31B. The mixture-of-experts 26B sits at bf16's pace, and the 4-bit builds run at 0.14x to 0.69x at every size.

Llama Village: a virtual world powered by local AI with llamadart

Llama Village in motion. The characters’ dialogue is generated by an on-device model. Watch the...

I got Jev to zero mistakes. I'm still using Flash-Lite.

Jev is a brilliant decision model. Gemini Flash-Lite is the model nobody talks about, and it’s fast,...

Gemma 4 E2B on an AMD MI300X: Which Weight Format Should You Serve?

Ten builds of Gemma 4 E2B (bf16, fp8 in both E4M3 flavours, int8 W8A8 and int4 W4A16, each with and without int4 embedding tables) served one after another on one AMD Instinct MI300X with the same vLLM image. fp8 is the only format that keeps pace with bf16, the 4-bit builds run at 0.14x to 0.63x, and int4 embedding tables cost almost nothing.

Making cross-platform local AI easier with llamadart

My writing assistant could talk to Gemini. The missing piece was using it without a connection. That...

Welcome Thread - v 396

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

stop-using-complex-urls-for-your-demos.us-central1.run.app

Wish you had a custom domain for all of your demos and AI prototypes? When you deploy your apps with...

Run, Hunt, Hack: Join the Cloud Run Hackathon on Product Hunt

Got a cool side project running on your local machine? This is your chance to make it live and have...

Build a Tiny Virtual Pet on Arduino in 60 Minutes 🐾

Turn an Arduino Uno Q into Kiku, a Tamagotchi-style virtual pet with an animated LED face, moods, and keyboard controls.

Why you still need a Website Portfolio, even though everyone can Vibe Code it.

If you have been following me for a long time, you already know I have been holding off my Portfolio...

Join the Hacktoberfest Weekend Challenge: Build for a Friend! $2,450 in Prizes Across 17 Winners. Submissions Due October 5 at 6:59 AM UTC.

Hacktoberfest is here, and so is the first of our five Hacktoberfest DEV Challenges: a Weekend...

Hacktoberfest 2026 DEV Challenges: Five Challenges, One Prompt, a New Theme Every Week

Hacktoberfest is here, and this October we're running five DEV Challenges back to back. Every...

The Physics of Socratic Prompting: Somatic Recoil, Chess Alpha-Beta, & The NLP Meta-Model

Why scalar RLHF fails at credit assignment, why barking direct code fixes turns you into an exhausted human compiler, and how Socratic questioning plus topological scars prune doomed search trees at depth d=1.

Everything You Need To Know About Hacktoberfest 2026: AI Belongs to Everyone 🎃

It's October 1st, which means Hacktoberfest 2026 is officially live! 🎉 This year looks a little...

Join Us Live: Hacktoberfest 2026 Launch with Exclusive Swag! 🎃🚀

Hacktoberfest officially kicks off October 1st! To celebrate, we are hosting an official launch...

Gemini 4 Argon https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/

...

Gemma 4 on Amazon SageMaker: The NVIDIA T4 Decodes at 0.8x of the L4 With the Same Answers

Gemma 4's 4-bit builds on SageMaker's smallest GPU, an NVIDIA T4, against the L4: a Turing patch for vLLM, the host image the CUDA 13 container needs, speed, memory, answers and cost per token.

Gemma 4 on a Tesla T4, Part 3: Int4 Embeddings Serve E2B in 2.86 GiB at 2.30x bf16

Google's QAT Gemma 4 E2B keeps its embedding tables in bf16, and on a Tesla T4 they are most of the model. Packing them to int4 on the grid QAT trained them onto cuts model loading from 6.33 to 2.86 GiB, with every greedy test output token-identical, and raises vLLM's output throughput 11-37% over Google's own W4A16 export.

Welcome Thread - v 395

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

How to Build a Real-Time Voice AI Agent with the Gemini Live API

This post was originally posted on X, by Annie Wang, Developer Relations Engineer, Google Cloud and...

Count It or Compute It: When a Tool Returns Rows, the Models That Count Them Right Spend the Tokens

A Kaggle benchmark of the step agents rarely test: counting what a tool returns. Ten models, 68 questions, one tool that returns the count and one that returns the rows. With the count, every model is right at a flat cost. With the rows, models that reason through the list count 330 ids right and spend 6 to 26 times the tokens doing it; models that answer straight away get 0 to 10 of 21.

I connected a fruit fly connectome to tic-tac-toe (with a minimax safety net)

Scientists have mapped the whole nervous system of a fruit fly: every neuron and every connection, in...

Claude on Google Cloud workshop | NYC | 9/30

On Wednesday, September 30, Anthropic and Google Cloud are co-hosting a hands-on developer workshop...

Building File4Base: The Modern, Open-Source Alternative to old file bases (Powered by Antigravity)

For decades, platforms like Claris FileMaker, Microsoft Access, and 4D enabled businesses to build...

This video is about how this video was made

This video (the script, the voice timings, the source code, the storyboard, the briefs the subagents...

Congrats to the Summer Bug Smash Winners!

We are thrilled to announce the winners of DEV's Big Summer Bug Smash powered by Sentry! This...

Running a Jev-Style Decision Model on One TPU v6e: What Fits, What It Costs, and What Changes From a GPU

Gemma 4 E2B, E4B, 12B and a 26B-A4B fp8 build read by their label probabilities with vLLM on one TPU v6e chip, checked against the same read on an NVIDIA L4 and against Jev 1.13.0's published results. What fits one chip, how to read labels when vLLM on TPU returns only the top 32 log-probabilities, speed, cost, and why no 31B loads today.

Deploying LiteLLM: An Open-Source AI Gateway

LiteLLM is an open-source AI gateway that provides a unified, OpenAI-compatible API for over 100...

Disappeared Since March: Taking a Long Break Was My Best Decision Yet

If you checked my profile recently, you probably noticed my page has been completely quiet since...

Welcome Thread - v 394

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

I Turned DEV.to Into a Walkable 3D Library — Debugging It Has Been a Nightmare

DEV Library is my idea of first-person 3D reimagining of DEV.to. Not a themed scene with some...

Claude Opus 5.5 is now available on Google Cloud

Everyday complex tasks? No problem. Opus 5.5 handles long-running coding and knowledge work while...

Share State Across Dart Isolates Without Losing Your Mind: Enter shared_map

How to bypass tedious SendPort/ReceivePort plumbing and share synchronized in-memory state across Dart Isolates using the zero-dependency shared_map package.

Dart Enhanced Enums Are Secretly Factories: Unlocking Constructor Tearoffs

How combining Dart's Enhanced Enums with constructor tearoffs turns simple enum values into self-instantiating, type-safe polymorphic factories.

Stop Paying the build_runner Tax: Why I Refuse to Use Mockito in Modern Dart

Why code-generated mocks ruin developer velocity in modern Dart and Flutter, and how switching to mocktail restores true zero-friction TDD.

Architecting a Resilient DevSecOps Pipeline for Enterprise AI Agents

A four-stage DevSecOps CI/CD architecture for securing enterprise AI agents with GitHub Actions, secret scanning, AI-assisted review, Veracode SCA, and Pipeline SAST.

Serving Gemma 4 on an AMD MI300X: What $1.99 an Hour Buys

A step by step deployment of Gemma 4 E2B to a single AMD Instinct MI300X on AMD Developer Cloud, driven by Python MCP tools, and the throughput a 191.7 GiB card returns for its hourly rate.

Congrats to the DEV Weekend Challenge: Dog Days Edition Winners!

The results are in for our DEV Weekend Challenge: Dog Days Edition! Thank you for your patience while...

A Quick Update on the Summer Bug Smash Winners

Hey all, we have a quick update for everyone who participated in DEV's Big Summer Bug Smash powered...

An MI300X Over MCP: What the Matrix Cores Execute, and What They Don't

One AMD Instinct MI300X on AMD Developer Cloud, managed entirely through a tag-scoped Python MCP server, with every figure read off the card rather than a spec sheet. fp8 e4m3fnuz runs 1.77x bf16; int8, which AMD rates identically to fp8, runs 0.69x; fp4 is not on this silicon at all. One droplet, $1.99 an hour, and two readings that were wrong the first time.

Build real-time voice applications with Gemini 3.8 Live and 3.5 Transcribe

Yesterday, we released new Gemini Live models in the Gemini API and Google AI Studio, expanding our...

Welcome Thread - v 393

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

How we built a desktop companion robot with Gemma 4 and Raspberry Pi

The behind-the-scenes story of how we built DinoDesk AI—a privacy-first, LEGO dino companion robot powered by a hybrid Local Gemma 4 and Cloud Gemini architecture.

Build in the VM, Think on the Mac GPU: Debian 13 on Apple container With a Local Gemma 4

Apple's container CLI 1.4.1 cannot boot the official debian:13 image as a machine, because it has no /sbin/init. A small Dockerfile fixes that and gives you a persistent Debian 13 VM with systemd, your Mac user and your home folder. The VM has no GPU, so Ollama runs on macOS and the VM calls it at 192.168.64.1:8000. From inside Debian, gemma4:e2b answered at 45.2 tok/s, loaded 100% on the M3 GPU.

The Symmetry of State: Why Flutter Deserves context.value and context.state

Eliminating the widget builder tax, closure fatigue, and the context.watch trap in Flutter: how 1:1 symmetry between containers and BuildContext unlocks cleaner, faster reactive apps.

is Graph Engineering just reinventing systems architecture for the AI age?

Bringing backend predictability to multi-agent systems I've been hearing the phrase "graph...

Gemma 4 on an 2021 4 GB Laptop GPU: QAT Takes It From 9.5 GiB to 1.6

Step-by-step: running Google's quantization-aware-trained Gemma 4 E2B on a 10th-gen Core i7 laptop with a 4 GB GTX 1650 Ti — why bf16 and int8 cannot fit, why the QAT GGUF does with room to spare, and managing it with an MCP server.

DEV Weekend Challenge: Dog Days Edition Winner Announcement Delayed

Hey all, we have a quick update for everyone who participated in the DEV Weekend Challenge: Dog Days...

Congrats to the Frontend Challenge: Comfort Food Edition Winners!

We are so excited to announce the winners of our Frontend Challenge: Comfort Food Edition! This...

Four Debian 13 Boxes, One Brief: 1,923 Packages on Metal, 328 in the Cloud

The same Debian 13 on a laptop and on AWS, GCE and Azure. The cloud images ship 328-350 packages against 1,923 on metal, no firmware package at all, and no tool to read the NVMe they all boot from. Each machine was then given the same brief and asked to analyse itself. Three of them agreed. The fourth found a partition table its own resize had broken.

The Modern Pitch for BlocSignal: Why Engineering Leads Are Moving to Reactive Primitives

A comprehensive guide for tech leads, staff architects, and engineering managers evaluating BlocSignal: cutting through CISC ceremony, unlocking AI agent velocity, eliminating the code-gen tax, and mastering push-pull reactivity.

4 pitfalls of loop engineering (and how to fix them)

Perhaps you've heard the term Loop Engineering: instead of solving a problem by hand, you build a...

Welcome Thread - v 392

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

Interactive AI Eval Dashboards with Data Studio

Welcome to the final entry of our series about designing, analyzing and visualizing AI evals! As with...

Bidirectional Writeback for Apache Iceberg via Google Sheets: Serverless Lakehouse Console

Turn Google Sheets into a Fully Interactive, Differential ACID Mutation Console for Apache Iceberg...

Serverless Multimodal Vector Search on Apache Iceberg via Google Apps Script

Turn Google Drive into an AI-Powered Lakehouse Vector Engine across Converted PDFs, Binary Images,...

BoonFest: The Anti-Sloth Game Where Generosity Means Survival!

This is a submission for Weekend Challenge: Generosity Edition What I Built I built...

My Grandmother Ran Ajo. I Built the Version Where the Pot Can't Walk Away

This is a submission for Weekend Challenge: Generosity Edition What I Built My late...

The Unbreakable Shopping Cart: Pairing BlocSignal with Fast Immutable Collections (FIC) for Bulletproof Flutter Apps

Eliminate in-place mutation bugs, corrupted undo stacks, defensive copying overhead, and skipped Flutter rebuilds by pairing BlocSignal with fast_immutable_collections.

Unifying Google Workspace and Apache Iceberg: Serverless Lakehouse Management

Turn Google Sheets into a Petabyte Lakehouse with Sub-Second ACID Queries. ...

AI Engineering Is Easy. Changing How We Work Is Hard

AI engineering sounds fancy. New terms are everywhere: agentic development, AI-native engineering,...

Join our DEV Weekend Challenge: Generosity Edition! $1,000 in Prizes Across FIVE Winners. Submissions Due September 7 at 6:59 AM UTC.

We're back with another DEV Weekend Challenge, a short bite-sized challenge planned to fit into your...

Kong AI Gateway 2.0 on Google Cloud: Securing GKE, Cloud Run, and Vertex AI(Agent Platform)

Most teams running on Google Cloud don't pick one compute model and stay there. Some services live...

Taming Flutter Infinite Scroll (Part 2): Turning ScrollController into a Reactive State Machine with CubitSignalMixin

Discover how to eliminate Flutter StatefulWidget boilerplate and overcome Dart's single-inheritance wall by combining ScrollController with CubitSignalMixin and BlocSignalMixin for a 100% StatelessWidget UI.

Your First Multi-agent system: A Beginner's Guide to Building an AI Trend finder with ADK

Welcome back to our series on building the ultimate AI research assistant for our AI agent podcast!...

Your First AI Agent: A Beginner's Guide to Building an AI Trend finder with ADK

The world of AI agents is moving at lightning speed. Keeping up with the latest trends, new...

I Built My First AWS Agent Workflow, and the Hardest Part Was Getting It to Stop Assuming Things

TL;DR I recently finished a project from Udacity's Future AWS Agent Engineer Nanodegree Program,...

ChromeOS Lookalikes, Two Ways: One With Drivers, One Without

chromeos-boot holds two unrelated scripts under one name: stage seeds a real Crostini container from a private bucket, flex skins a bare-metal Debian desktop to look like one. The split exists because Crostini's guest kernel can't load the NVIDIA driver.

Taming Flutter Infinite Scroll: Why 3 Lines of async* Missed the Point, and How BlocSignal Fixes It

Explore why using async* generators for infinite scroll pagination in Flutter hides subtle concurrency crashes, and discover how BlocSignal solves rapid scrolling race conditions streamlessly with droppable().

AI-assisted genealogy

My son recently came to me to brag about using AI to find our ancestors. While the results were...

20 Agentic AI Terms Every Developer Should Know (Explained Simply)

Do you ever feel like the AI world has moved forward a little too quickly? You hear about...

💎 Introducing Community Gems: Celebrating Human Curation and the Best of Our Community

In an internet full of noise, infinite scrolls, and algorithmically generated content, finding...

How to Write Reliable Rubrics for LLM-as-a-Judge Evaluations

Follow up to Part 1: How to Design AI Evaluations You Can Actually Trust At Google, we are...

What is harness engineering and why should I care?

How do you ship a software product with 0 lines of manually-written code? A friend...

Welcome Thread - v391

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

Hearing the Mountain's Roar: How Antigravity CLI's AI Agents & IoT Data Track Volcanic Shockwaves

Turning 29k home weather stations and Gemini AI agents into a 15-minute volcanic warning...

Preptember is here!! Plan a Fest for your local community.

September marks the official start of Preptember, a month dedicated to organizers planning local...

Three Gemma 4 Deployments on One T4G for Under $3: What the Runtime Changes, and What It Doesn't

vLLM, JAX and PyTorch serving the same Gemma 4 E2B checkpoint on the same AWS G5g GPU, on one harness and one statistic. The decode ranking reverses on boot time. Nineteen instances, four and a half instance-hours, under $3 - which is what let five wrong claims get caught.

How to Design AI Evaluations You Can Actually Trust

As part of my work at Google, we are publishing a suite of Agent Skills for Google products and...

Streamline Publishing with a Claude Code Skill

A Claude Code skill that turns one markdown file into dev.to, AWS Builder Center, Medium and LinkedIn versions, checks them before they ship, and posts the ones with an API — plus the debugging tools for when a destination mangles something.

The job description already changed. We're not coders anymore, but couriers.

re: Couriers, Not Coders (Syntax Isn't The Edge Anymore) ...

Automate Flutter's New Split Package Migration with AI Agent Skills

How to use dart-sdk-skills to empower your AI coding agent to seamlessly migrate Flutter projects to standalone material_ui and cupertino_ui packages.

Native CORS support on GKE Gateway: Offloading cross-origin policy management to infrastructure

Offload cross-origin preflight handling and header injection to Google Cloud Load Balancing with native CORS support on GKE Gateway.

Overcoming Dart's Single Inheritance Wall: Composable CubitSignalMixin & BlocSignalMixin in Flutter

Discover how CubitSignalMixin and BlocSignalMixin allow any existing Flutter controller, domain repository, or enterprise class to gain full reactive state container capabilities without occupying its single inheritance slot.

What should the next Weekend Challenge theme be??

The next DEV Weekend Challenge launches next week, and we have some ideas up our sleeves, but we...

Grand Central Station: Why BLoC, Riverpod, and BlocSignal Are Now True Peers

Discover why Flutter state management is no longer an all-or-nothing choice. Explore how BlocSignal, Classic BLoC, and Riverpod now operate as first-class bidirectional peers at the Grand Central State Terminal.

Unlocking workload rightsizing visibility on GKE: How VPA decision logs bring observability to autoscaling

Learn how to troubleshoot and audit GKE Vertical Pod Autoscaler actions with structured decision logs in Cloud Logging.

Stop Wrestling with ASR: The Complete Guide to Gemini 3.5 Transcribe 🎙️

You’ve probably used Gemini to analyze hours of video, summarize podcasts, or answer questions from...

Kubeflow Without Kubernetes? Deploy a Complete MLOps Suite in 60 Seconds with Gubernator

Run JupyterLab, MLflow, MinIO S3, and Ollama Inference on a lightweight cluster using pure Docker Compose and <2GB RAM.

Two-step control plane upgrades in GKE: How minor version rollbacks work under the hood

Learn how GKE decouples binary rollouts from API finalization to safely test and roll back Kubernetes minor version upgrades.

Cross Cloud A2A Agent Card Field Comparison

Comparing Agent Cards with A2A - This tutorial aims to fetch the agent card from A2A agents running...

The agent posted successfully. To the wrong account.

Back in July I wrote about what it takes to wire an AI agent into social platforms: six OAuth flows,...

Vector Search Is Still the Memory Layer Agents Actually Need

When I was working on Vector Search with JavaScript, vector search was a hot topic. By the time the ...

[Go in Practice] Writing Modern Go with AI: Testing JetBrains go-modern-guidelines and Refactoring a 1,039-line main.go

Background In the AI era, even I delegate most of my code optimization or writing tasks...

FutureBuilder and StreamBuilder as Anti-Patterns: Why Your Async Boundary Should Be Far Away From Your Views

Discover why using FutureBuilder and StreamBuilder inside Flutter widget trees breaks separation of concerns, triggers accidental refetches, creates layout shift cascades, and hinders testability—and learn how to quarantine async at the perimeter using AsyncSignal and BlocSignal.

Introducing AI Disclosure on DEV: Tools for Nuance, Clarity, and Better Feeds

We're introducing structured AI disclosure tiers to foster transparency, preserve human connection, and give you control over your reading experience.

I Counted the Attack Vectors in Our AI Stack and Now I Can't Sleep

so a while back i did something i do not recommend before bed. i counted the vendors in a normal...

Welcome Thread - v390

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

Taking control of cluster security: A deep dive into GKE ClusterNetworkPolicy

Discover how GKE ClusterNetworkPolicy enables platform teams to establish global security guardrails without hindering developer agility

What Do You Do While AI Codes?

AI coding agents leave you with 5-to-20-minute gaps all day. Five real ways I fill them — and the one "quick" habit that makes you the bottleneck.

AI Evals at a Glance: Heatmaps for Stakeholders

Visualizing AI evals with Inspect Viz Welcome back to our blog series on running,...

comiCSS #255: Yellow

comiCSS cartoon for August 24, 2026

Tech webinar: How to control costs & measure ROI for Claude Code on GCP - 9/1 12pm PT.

If your team is running or planning to deploy Claude Code on Google Cloud, managing spend and...

The data is in: AI is how developers learn now

AI is now the most common way that new developers learn. We all knew AI was having an impact on...

Bridging the AI Cutoff: Teaching Coding Agents Every Dart Feature from 1.0 to 3.14

How to eliminate LLM training cutoff gaps in Dart and Flutter, modernize legacy codebases, and install open agent skills with a single command.

HTML is getting cool again: Meet the Invoker Commands API

For years, frontend development has had a slightly embarrassing relationship with HTML. We all read...

When to Use Bloc vs. Cubit vs. Signal: An Architectural Decision Guide

Stop guessing how to structure your Flutter state. Here is a definitive, 4-tier decision rubric comparing raw Signals, CubitSignal, BlocSignal, and persistence mixins.

Hacktoberfest 2026: AI belongs to everyone

We have some news we're excited to share today: Major League Hacking (MLH) and DEV are partnering...

Greatness Is Forged by Limitation

Can't believe I spent 2 weeks writing this. Last week, I gave a talk at a Cursor community event...

Welcome Thread - v389

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

Coding agents got boring the moment we built a really good one.

MESSAGE FROM BACKBOARD.IO Co-Founder Rob Imbeault: Coding agents got boring the moment we built a...

Git Gud!

You heard me. Alright, that was mean lol. Though based on the title, you probably already knew the...

[Dev Log][Python] Create short videos from photos and clips with Gemini 3.7 Flash: ReelCraft

Preface: It all started with a misunderstanding. I noticed a new page in the Gemini API...

Join our DEV Weekend Challenge: Dog Days Edition! $1,000 in Prizes Across FIVE Winners. Submissions Due August 17 at 6:59 AM UTC.

We're back with another DEV Weekend Challenge, a short bite-sized challenge planned to fit into your...

It's always Doom https://ood.dev/posts/doom/

...

Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU

A field report on serving Gemma 4 E2B under vLLM on AWS G5g — the only aarch64 + SM 7.5 hardware there is. No published build covers that combination, AWS quietly solves half of it, and the thing that actually blocks you is 64 KiB of shared memory.

I Stopped Trusting AI Agents With Tools. So I Built a Gatekeeper.

Update 08/15 0.2.0 Released github.com/deghosal-2026/agent-tooltrust · pip install agent-tooltrust...

Do I Still Need a Monkey Patch for Gemini Live?

No. And deleting 187 lines of it was the single biggest benefit of moving to ADK 2.x — but it was not...

Riverpod to BlocSignal: Incremental Migration and Zero-Codegen Signals for Flutter

Learn how to trial or incrementally migrate from Riverpod to BlocSignal with zero code generation, fine-grained signal graph reactivity, and bidirectional interop.

Managed Inference on Google Cloud: Pairing the Gemini Enterprise Agent Platform with Cloud Run

Learn how to run managed AI inference on Google Cloud by pairing the Gemini Enterprise Agent Platform with Cloud Run — with architecture, code, deployment, and security explained step by step.

Welcome Thread - v388

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

Bug Smash: restoring dropped Gemini chat config in Sentry's JavaScript SDK

This is a submission for DEV's Summer Bug Smash: Clear the Lineup powered by Sentry. ...

Latency vs. Tokens: What I Learned Optimizing an Agent with Gemma (and What Didn't Work)

I'd been waiting for more than 30 minutes. The terminal just sat there, blinking, without returning a...

How Many Introductions Away Are You From Pedro Pascal? A Practical Introduction to Graph Search

I was watching The Mandalorian the other day when it struck me that I don't know Pedro Pascal, which...

Hey all! I’m Jem, the DEV Community Program Coordinator

It feels good to finally be writing this. I've been working part-time behind the scenes at DEV for...

I Joined dev.to because...

Why not? Just kidding, there is more to it. Just thought it flows well with the title...

Backend Engineer (Me) Ships a Browser Game With One Unintentional System Requirement: My Monitor

This is a submission for DEV's Summer Bug Smash: Smash Stories powered by Sentry. Prefer...

Agent Sandboxes: Giving AI Agents Their Own Little Linux Box (And Why You Should Care)

Sourced from: GKE Agent Sandbox docs, kubernetes-sigs/agent-sandbox So here is the thing. We...

linkedSignal() Writes Back: A Trace Through the Reactive Graph 🔍🚀

Let's be honest: linkedSignal() always had a bit of a split personality. It read beautifully from...

General Challenge Updates Moving Forward

Hey all, as part of our expanding challenge program we want to update and clarify some challenge...

Serving Gemma 4 2B on a Single TPU v5e Chip with MCP and Antigravity CLI

This article is the v5e follow-on to the v6e-1 debugging guide. Same MCP tooling, same Antigravity...

Welcome Thread - v387

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

Exploring Form Management Patterns in Flutter with BlocSignal

Master form handling in Flutter with BlocSignal. Learn how to separate Primary vs. Derived state using computed signals, compare 3 clean form architectural patterns, and pick the right one for your app.

Kiro Crew: The Next Frontier

I enter the bridge of my ship, the Kiro Enterprise. I see my crew ready for my command. The agent...

How to Build a Local AI Workspace Like PewDiePie's Odysseus: Hardware, Models, and Cost

A practical, source-backed guide to building a local AI workspace like PewDiePie's Odysseus, including VRAM tiers, realistic budgets, model runtimes, installation steps, and security advice.

Your RAG copilot can't count — stop letting it try

Your RAG copilot can't count — stop letting it try A user asked our document-search...

Congrats to the DEV Weekend Challenge: Passion Edition Winners!

We are excited to announce the winners of our DEV Weekend Challenge: Passion Edition! The prompt was...

Skills vs MCP: How AI tools have evolved

Eighteen months ago, MCP was the thing. Every demo and chatbot connector was running on MCP under the...

Does it still make sense to learn how to code?

Does it still make sense to learn how to code? This is a question I’ve been thinking about a lot...

Gubernator Weekly Update: CoreDNS Aqueducts, SRE Stack, Network Topology & Cluster Auto-Updates!

Gubernator Weekly Update: CoreDNS Aqueducts, SRE Stack, Network Topology &amp; Cluster...

Data, Context & RAG Lineage Governance for Enterprise AI Agents

A deep-dive architectural guide to query-time ABAC, cryptographic lineage, and outbound payload sanitization in agentic RAG systems.

One TPU Chip, Eight Agents: Serving Small Agent Workloads with Raw JAX

Cloud TPU v6e-1 (ct6e-standard-1t, one v6e chip, 32 GB HBM), GCE flex-start, europe-west4-a. vLLM...

Amazon Bedrock Agents Orchestrating Google ADK over A2A

This article explains how to build and test a cross-cloud currency agent. An Amazon Bedrock master...

Join our latest Frontend Challenge: Comfort Food Edition 🍲

We're back with another Frontend Challenge, and this time we're hungry! 🍜🥧 Running through August...

What is current your "daily driver" coding model? (July 2026)

Fable 5 at Max effort? OpenAI's gpt-5.6? The latest Gemini models? Perhaps Kimi K3 or other...

Welcome Thread - v386

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

Can Google ADK Talk to Amazon Bedrock AgentCore Runtime? A Cross-Cloud A2A Benchmark

This article provides a step-by-step guide to building and testing a cross-cloud currency agent. A...

Building AI Agents with the Kotlin Agent Development Kit (ADK)

This tutorial builds a starter "Hello World" style agent using Kotlin and the native Kotlin version...

Bug Smash isn't glamorous and that's what I love about it.

We kicked off DEV's Big Summer Bug Smash on July 14, and I've been waiting to write this post since...

DevRelCon, Adult Summer Camp, and My First Time Speaking

There’s something about DevRelCon that feels a little like adult summer camp. It’s immersive,...

I had two weeks, an 8-foot keyboard, and a Wordle Workflow

A Wordle clone, an 8-foot keyboard, and a holographic fan display made Temporal's Durable Execution visible at AI Engineer World's Fair.

Your Face on a World Cup Sticker: Our Nano Banana Story

There is something timeless about opening a pack of football stickers. You never know which player,...

React 19's useActionState Showed Me Why Disabling My Submit Button Was Never Enough

Every form I ever shipped before React 19 needed the same three pieces of state, and I wired them up...

Passkeys Explained Simply

You’ve probably seen that little prompt that says “Sign in with Face ID” or “Use a passkey” instead...

Can Google ADK Talk to Microsoft Foundry on Azure? A Cross-Cloud A2A Benchmark

This article provides a step-by-step guide to building and testing a cross-cloud currency agent. A...

Switching Tracks in BlocSignal: The Universal State Switchyard for BLoC, Riverpod, and Provider

Stop derailing your Flutter apps! Learn how BlocSignal acts as a central railway switchyard bridging BLoC, Riverpod, and Provider synchronously without microtask stream latency or heavy code generation.

Auditing Agent Skills: A Threat Model for the Next Generation of AI Package Managers

Let me start with a question. If a stranger handed you a USB drive and said "plug this in, it just...

I Built Something Good With AI. Now Some Developer Communities Don't Want to See It.

I recently tried to share an open-source project I've been working on called Open Vectorizer. It's a...

Investing in multi-agent AI safety research

Scaling AI Safety Research for a Multi-Agent World For the past decade, we've focused on making...

Teaching Google Antigravity to Paint: A Stateful Image-Editing Skill Built on Gemini's Interactions API and MCP

How nb2lite-skill-agy packages Google's gemini-3.1-flash-lite-image as an Antigravity skill + MCP server — with multi-turn stateful edits, a simple install guide, and a dogfooded cover image.

Teaching Antigravity to Direct: A Stateful Video-Editing Skill Built on Gemini's Interactions API and MCP

How omni-skill-agy packages Google's gemini-omni-flash-preview as an Antigravity CLI skill + MCP server — what Omni Flash actually does, a field guide to all eight tool calls, multi-turn stateful edits, an idiot-proof install guide, and a one-tool-call path to YouTube.

Zero to Multi-Region: High Availability Serverless with Cloud Run and Cross-Region Failover & Failback

Google just made multi-region Cloud Run significantly easier. Here is the full picture; what changed,...

Teaching Codex to Paint: A Stateful Image-Editing Skill Built on Gemini's Interactions API and MCP

How nb2lite-skill-codex packages Google's gemini-3.1-flash-lite-image as a Codex skill + MCP server — with Codex-native install paths, stateful edits, and a dogfooded cover.

Teaching Claude Code to Direct: A Stateful Video-Editing Skill Built on Gemini’s Interactions API…

Teaching Claude Code to Direct: A Stateful Video-Editing Skill Built on Gemini’s...

Better than Next.js? Is Rust Finally Ready for Full-Stack Web Development? Introducing Topcoat

There is a super-new Rust Web Framework in town, and it's name is Topcoat Rust is already a solid...

Loop Engineering: How to Stop Your Agent Reward-Hacking Its Own Checks

You gave the agent a failing test and told it to get the suite green. It came back green. Then you...

New Gemini models dropped https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-6-flash-3-5-flash-lite-3-5-flash-cyber/

3.6...

Gemini 3.6 Flash & 3.5 Flash-Lite: Developer guide

Gemini 3.6 Flash (gemini-3.6-flash) and Gemini 3.5 Flash-Lite (gemini-3.5-flash-lite) are generally...

Google Cloud Labs: Accelerate AI with Cloud Run

Moving Beyond the Prototype The AI landscape has shifted. While "vibe coding" with tools...

Gemma 4 E2B on a Single TPU v6e Chip: A Serving Deep Dive

What it took to deploy, why the QAT checkpoints refuse to load, and what one flex-start v6e chip is actually worth — measured live.

tpu-management: a Claude Code skill for running Gemma 4 on Cloud TPUs

A Claude Code skill + MCP server that provisions Google Cloud TPU capacity, serves Gemma 4 with vLLM, benchmarks it, and tears it down — installable in one command.

Gemma4 DevOps In Action

In the last entry I got Gemma-4's 128-expert MoE running on an inf2.24xlarge and signed off with...

Context Is King: Rethinking Domain Ownership, Product, and the "Spec Phase"

If you’ve spent any time recently writing detailed product requirement documents or meticulously...

AI And Code Ownership: Who Is Responsible For Generated Code?

Imagine your AI assistant just produced 200 lines of code. Legally, you may not own a single line of...

From Apple Health Data to Clinical Storytelling: Building an AI-Powered Report with Python and Gemini

Introduction At recent technology conferences, one topic has caught my attention: every...

I've Spent 10+ Years in Software Engineering. After Sickness, Burnout, and a Layoff, I'm Rebuilding My Career. Ask Me Anything

Hi, I'm Cesar, a Senior Software Engineer with 10+ years of experience. In 2023, I got sick and...

Five Gemma-4 models, one accelerator: what porting E2B 31B to AWS Inferentia2 taught me

I ported the whole Gemma-4 family — E2B, E4B, 12B, 31B, and the 26B-A4B MoE — to run on...

Hey DEV, I'm Tobore. Let's actually connect.

Hey DEV, I'm Tobore. Let's actually connect. I've been on here for a while now, mostly writing and...

I burned through thousands of AI tokens. Then a friend did it for free

(yep, kinda clickbait, just for the funsies 😊) At the beginning of the year, I relaunched my...

What is an "agentic harness," actually?

I've been hearing the word "harness" thrown around a lot lately. I assumed it just meant "the IDE" or...

Did You Know TLDs Can Be Websites?

You've probably registered a domain with Route53 or another popular registrar. You pick something...

Claude might be saturating your machine

My laptop was sitting idle with the fan at full tilt. Nothing was running that I knew of. The culprit...

DiffusionGemma: The Developer Guide

Following our announcement in our launch blog post, we are sharing this developer guide to help you...

Why did my benchmark stop at N=22? A debugging story in nine bugs

Submission for DEV's Summer Bug Smash — Smash Stories track. There was a file in my repo called...

My benchmark's Python column was N/A for a year — CPython's 4300-digit limit, and eight other bugs

Submission for DEV's Summer Bug Smash — Clear the Lineup track. The...

TPU Deployments with Gemma 31B, v6e-8, and Antigravity CLI

This article provides a step by step debugging guide for deploying Gemma 4 to a Google Cloud TPU...

Welcome Thread - v384

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

5 Trends That Defined AI Engineering at World’s Fair 2026

At this year's AIE World’s Fair, AI engineering entered a new phase: building systems around...

DEV’s Big Summer Bug Smash is now LIVE! Share $5,000 in cash prizes, skateboards, and more across 20+ winners. 🐛🐞🪲

Today is National Be Nice to Bugs Day in the U.S. and we’re thrilled to launch our Big Summer Bug...

Building a Hybrid Docker Orchestrator in Go: The Journey from Single VM to Multi-Node Cluster

What if you could combine the native simplicity of Docker Compose with the decentralized targeting...

Chasing the Sentry prize for DEV's Summer Bug Smash? Let us know what questions you have.

DEV just kicked off their Big Summer Bug Smash, an event all about fixing bugs and optimizing...

How I made a Rust hot path 27x faster, and the AI fix I refused to merge

Two years ago I open-sourced KeyEcho, a small desktop app that plays a mechanical-keyboard sound the...

This is remarkable https://bobdahacker.com/blog/fifa-hack

I...

26B Gemma 4 QAT Deployment with GCE g2-standard, NVIDIA L4, MCP, and Antigravity CLI

This article provides a step by step deployment guide for Gemma 4 to a Google Compute Engine hosted...

HTTP gets a QUERY method so complex searches can stop pretending to be POST https://www.theregister.com/devops/2026/07/13/http-gets-a-query-method-so-complex-searches-can-stop-pretending-to-be-post/5270192

...

4B Gemma 4 QAT Deployment with GCE, NVIDIA L4, MCP, and Antigravity CLI

This article provides a step by step deployment guide for Gemma 4 to a Google Compute Engine hosted...

I Finally Built the Dev Opportunity Radar Website ❤️

This is a submission for Weekend Challenge: Passion Edition 📌 TL;DR I found this challenge on the...

The Myth of the Post-Documentation Era

There is a growing sentiment in engineering circles right now that documentation is a relic of the...

Building an Agentic FinOps Platform — Development Environment Setup, Google Antigravity, MCPs and Skills, and ADK Bootstrapping with Agents CLI

TL;DR — This article is going to be jam-packed with useful information, tips, tricks and hacks for...

A lot of good points here https://antirez.com/news/169

antirez.com

Porting Gemma-4 (2B / 4B / 12B) to AWS Inferentia2

A field report on running Google's Gemma-4 on AWS Inferentia2: mixed attention heads, the vLLM / optimum-neuron / NxD dead-ends, and the neuronx-cc compiler limits.

2B Gemma 4 QAT Deployment with GCE, NVIDIA L4, MCP, and Antigravity CLI

This article provides a step by step deployment guide for Gemma 4 to a Google Compute Engine hosted...

Context bankruptcy: The case for strategic forgetting for AI Agents

Most of us have seen a coding agent fail to complete a task we know it can do. We just don't...

Is It Ethical to Post and Ask About Circuits on Dev.to?

I’ve been thinking about sharing some electronic circuit posts on Dev.to — small circuits, DIY...

Join our DEV Weekend Challenge: Passion Edition — $1,000 in Prizes Across FIVE Winners! Submissions Due July 13 at 6:59 AM UTC.

Hello! We're kicking off another DEV Weekend Challenge, a short bite-sized challenge planned to fit...

Guarding the till while autonomous data agents do the digging

Autonomous agents are genuinely good at answering messy business questions. Give one an LLM and a set...

Return on Attention: Why AI Code Reviews Are Wearing Us Out

PR volume went up, ticket quality didn't, and the gap got filled with LLMs on both sides of the review: bots reviewing, bots replying, bots occasionally arguing with bots about priorities that only existed in a teammate's head. Our CEO named the actual problem, and it's bigger than code review.

Congrats to the June Solstice Game Jam Winners!

We are so excited to announce the winners of the June Solstice Game Jam, our celebration of the...

Should I quit IT or just live through the burnout?

Some of you may have noticed I disappeared a bit from the community over the last couple of weeks....

Debugging Deployments with Gemma 4B, TPU v6e-1, MCP, and Antigravity CLI

This article provides a step by step debugging guide for deploying Gemma 4 to a Google Cloud TPU...

Debugging Deployments with Gemma 2B, TPU v6e-1, MCP, and Antigravity CLI

This article provides a step by step debugging guide for deploying Gemma 4 to a Google Cloud TPU...

✨Cool Effects, TTS, and Fun Animations (AI Avatar v15: VS Code and Chrome Extension)

Intro AI Avatar is a completely free app that lets your VRoid (VRM) 3D avatar animate in...

Debugging Deployments with Gemma 4B, TPU v6e-4, MCP, and Antigravity CLI

This article provides a step by step debugging guide for deploying Gemma 4 to a Google Cloud TPU...

Master Local Fine-Tuning with "gemma-trainer"

Take control of your AI models with our newest skill, designed to make local fine-tuning efficient.

A Third Brain for your Second Brain

The concept of the "second brain"/"knowledge base" is one of my absolute favorite nerd snipes of all...

Choosing the Right Tooling Layer for Your Agent

Selecting the right abstraction layer is not a new problem in software. It's common to have some...

The Conspiracy Big Software Engineering Doesn't Want You to Know

Buckle up, gang — it's conspiracy theory time. I've had this theory percolating in the back of my...

Protect Yourself, Mesh Yourself

In my last post, my SSH keys moved off disk and into 1Password. This one is about the network those...

Congrats to the GitHub Finish-Up-A-Thon Challenge Winners!

We are so excited to finally announce the winners of the GitHub Finish-Up-A-Thon Challenge, our...

Let Us Be Free

Nearly half a century ago, the free software movement made a demand that was both technical and...

18 Hot Takes On Where AI is Headed Next

by Peter Yang, Behind the Craft Today, I want to share 18 hot takes on where I think the AI market...

How Docusign is Bringing Contract Table Extraction to Production with NVIDIA Nemotron Parse

By Hiral Shah, Senior Director, Product Management, Docusign A major recurring theme among the...

Letting the DEV Community Weigh in on the Topics of AIE

I’m at the AI Engineer World’s Fair in San Francisco, where the vibes are enthusiastic. However,...

Without Structure

“Without structure, AI makes code worse.” - Tereza Tížková AI is a supercharger, not a magic wand....

These Founders Skipped Graduation To Be Here

When we met James Yang and Anish Paleja on Monday morning, The Daily Context team simply thought,...

I Tried to Escape LeetCode for 2 Years (But Here We Are)

Seriously, LeetCode in 2026? Everyone is saying HackerRank just killed LeetCode, and yet here I am,...

From Harness Engineering to Evals:

I’m at the AI Engineer conference in San Francisco this week. The event has every major brand-name...

Warp CEO Zach Lloyd on why software factories are the next phase of coding

I’ve been covering Warp for a couple of years now, and its rapid evolution from a command-line...

My First Year at DEV Recap

I heard about DEV a while back from a former colleague who was posting regularly back then. She won a...

Forward Deployed Engineers and the future of software engineering

Cover Image: Sierra’s Natalie Meurer at the AI Engineer World’s Fair today. Natalie Meurer is Head...

Play today’s game from Issue #2 of The Daily Context!

Yesterday, we kicked off our physical newspaper, The Daily Context, at the AI Engineer World’s Fair...

You Don’t Always Need The Frontier

Workshops at this year's AI Engineer World's Fair shifted noticeably away from RAG and prompt...

The Future Of AI Is Local And Open

There’s a specific moment that happens at every single hackathon. It’s usually around 2 or 3 a.m.,...

Gemma and sandboxing cause a stir at the World's Fair

As the AI Engineer World’s Fair kicked off officially on Monday, the halls were filled for the...

This Is Software’s iPhone Moment

In 2007, humans took roughly 85 billion photos a year. Photography was a specialized craft that...

Someone Else Pays for Your AI Access

you probably didn't think about this when you signed up. you entered your card details, verified...

Need a break? Play today's game from The Daily Context.

We (at DEV and MLH) are covering AI Engineer's World Fair by printing a physical newspaper called...

Welcome to AI Engineer World’s Fair 2026

Welcome to the first edition of the AI Engineer World’s Fair newspaper! On behalf of the organizing...

My commit message said "You've hit your session limit"

How I ended up running a local LLM to generate my git commit messages

The Model Does Not Need Memory. The Situation Does.

I think I was asking the wrong question. For a while, the question was simple: does memory make...

What Actually Happens When You Call an LLM API

you've felt it. you type a prompt, hit send, and the response starts streaming in under a second....

What's Next for AI?

I have been writing about AI for quite a while now, but this is probably the first time I genuinely...

Never forget to enter the Stern Grove lottery again!

Browser automation with Playwright, Python, GitHub Actions, and Entire to auto-enter San Francisco Stern Grove concert lotteries each week!

Not Enough SMEs or Customers to Make Your Evals? Make Some!

How to build grounded, validated user personas and turn them into agents that generate eval data, for when you cannot reach real users or SMEs yet.

Lite-Harness SDK

Unified API to swap AI coding harnesses like Claude Code and Codex

Did you want more Claude on Cloud? ☁️ Let's talk about Securing Agents at Scale

Did you want more Claude on Cloud? Well, look no further. We have something for you happening today...

Cognitive Pong: An Open Source Arena Where AI Agents Compete, Learn, and Train

An open source experiment exploring whether structured competition between AI agents can produce better reasoning, training data, and eventually better models.

Welcome Thread - v381

Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...

Function Names in JS Can't Contain Spaces, Right?

WRONG! Despite the widespread belief that function names in JavaScript MUST follow the...

Extending a Rust MCP/A2A Currency Agent with A2UI

Building an Agent with Rust,A2A, MCP, and A2UI This tutorial aims to extend and test a...

How My AI Agent Hacked Its Own Permissions (And What It Taught Me)

Have you ever tried to build an automation that works so well it bypasses the very rules you set for...

I Am Fired Up Again

A personal reflection on getting fired up again, chasing financial stability, building income that can outlast a job, and still loving the work I do today.

Debian Packages

Ubuntu OS (Operating System) is a distribution of Linux OS and is a derivative of Debian OS which is...

12B Gemma 4 Deployment with NVIDIA Blackwell 6000, QAT, MTP, and Antigravity CLI

This article provides a step by step deployment guide for Gemma 4 to a Google Cloud Run hosted GPU...

AI found 300 WordPress plugin zero-days in 72 hours. I build plugins. Here's what changed for me.

Before I released my own AI chatbot plugin, I ran it through a security review. It came back with 35...

Serverless Gemma 12B with NVIDIA A100 on Azure Container Apps

This article provides a step by step debugging guide for deploying Gemma 4 to Azure Container Apps. A...

What it takes to build docs worth reading

From 476 to 1,900+ commits: See how the Midnight DevRel team treated documentation like a product and completely transformed the developer hub.

Working on a silly project - share your favorite AI buzzwords/phrases and general key terms with me please!!

Feel free to include any brands or product names as well. Be as obscure or on the nose as you'd like....

Link or Button, that is the question.

What is a Link? Definition A link is an interactive element that redirects the...

12B Gemma 4 Deployment with NVIDIA Blackwell 6000, MCP, Cloud Run, and Antigravity CLI

This article provides a step by step deployment guide for Gemma 4 to a Google Cloud Run hosted GPU...

MTP Speculative Decoding with the 12B Gemma 4 QAT Model on NVIDIA L4, Cloud Run, MCP, and…

MTP Speculative Decoding with the 12B Gemma 4 QAT Model on NVIDIA L4, Cloud Run, MCP, and...

Skills over System Prompts: Building an Anki Tutor with the Antigravity SDK

AI has made me a little lazier. Not dramatically lazy. Not "the robots will do everything" lazy....

Congrats to the Hermes Agent Challenge Winners!

We are thrilled to announce the winners of the Hermes Agent Challenge! Over the past few weeks, the...

I'm not a developer, but I built a calendar app to fix my most annoying work task

I’m not a developer! I’ve never coded anything in my life. As far as I’m concerned, a Cloudtop is...

Building an agentic PR reviewer with Antigravity SDK

As announced in this blog post on June 18, 2026, Gemini CLI and Gemini Code Assist IDE extensions...

Congrats to the Gemma 4 Challenge Winners!

We are so excited to announce the winners of the Gemma 4 Challenge! This is officially our most...

How to Read a webrtc-internals Dump, Section by Section

When a WebRTC call goes bad, the browser already recorded what happened. Chrome keeps a live record...

Real-time IP capacity in Google Cloud subnets

When managing Shared VPCs, most teams allocate dedicated IP subnets for each service project to keep...

Debugging Deployments with Gemma 12B, TPU v6e-1, MCP, and Antigravity CLI

This article provides a step by step debugging guide for deploying Gemma 4 to a Google Cloud TPU...

Ask a DEV Community Mod!

Disclaimer: Please read the full post before commenting. Hey everyone! If you do not know me, my...

How We Saved Big and Simplified Our Image Pipeline: Adopting bunny.net on DEV

Hey everyone, Ben here. If you’ve been following the journey of DEV and our open source project...

12B Gemma 4 QAT Deployment with GCE, NVIDIA L4, MCP, and Antigravity CLI

This article provides a step by step deployment guide for Gemma 4 to a Google Compute Engine hosted...

Building a Chrome Extension to Make AI Use More Intentional

After posting several articles about the impact of AI on developers and sharing resources to help...

Letters to Tomorrow: A June Solstice Game About the Things We Carry Into Tomorrow

This is a submission for the June Solstice Game Jam 🎮 Play the Game: Letters to Tomorrow 💻 Source...

Meme Monday

Meme Monday! Today's cover image comes from the last thread. DEV is an inclusive space! Humor in...

Open Knowledge Format - portable digital map of your data as code

Yesterday Google dropped an article describing an interesting idea - a portable format for knowledge...

Turning Gemma 4 into an Old Korean Translator

There’s something uniquely beautiful about old books. The smell of weathered paper, the texture of...

Dialling Our Agents to 11: Agent Skills You Need to be Using!

What This Article Is About Howdy friends! Recently I wrote an article called Dialling Our...

Building Knowledge Graphs with Gemini

✨ Overview In this exploration, we'll see how to turn raw, unstructured documents into...

Dev Opportunity Radar #3: Neo Scholars, a $2M AI Challenge, and an $85K AI Fellowship

TL;DR Welcome back to Dev Opportunity Radar. This is a weekly series where I share opportunities,...

IOS Midsommer Madness

This is a submission for the June Solstice Game Jam Your Iphone can now celebrate the Solstace! When...

Why I still teach Singleton even though modules make it redundant

Ask any developer what design pattern they know best and Singleton comes up first. Ask the same group...

What was your win this week?

👋👋👋👋 Looking back on your week -- what was something you're proud of? All wins count -- big or small...

The AI Addiction Nobody Is Talking About

There is a particular kind of restlessness spreading through the tech world right now. It is not...

Your Vibe-Coded App Works. Is It Any Good?

TL;DR - Getting an app to run is now the easy part. AI is very good at producing something that...

System Design - A Frontend Engineer's Deep Dive

A walkthrough of designing a real-time collaborative whiteboard from a blank page to a production-ready architecture.

Congrats to the Google I/O 2026 Writing Challenge Winners!

We are so excited to announce the winners of the Google I/O 2026 Writing Challenge! We asked you to...

Virtual Coffee Needs Your Help

Virtual Coffee has always been a free, volunteer-led developer community supporting the tech...

Why New Language Features Need to Target AI Agents, Not Developers

AI agents are writing our production code. It's time to stop designing syntax sugar for humans and start optimizing languages for bots.

My daughter asked if developers used to write code by hand, but it was the follow-up question that surprised me.

My daughter Emma is 11. She's been vibe coding lately, and honestly, she's pretty good at it. The...

Celebrate June rituals with Solstice Bingo!

This is a submission for the June Solstice Game Jam Before we dive into technicalities, let me make...

I'm so tired to code. Not even Vibe Coding... D:

A post by FrancisTRᴅᴇᴠ (っ◔◡◔)っ

CSS – only a Nerdy Hobby?

In times when people believe that "AI can code a website in 2 days" (see: how to leverage AI as a...

Claude Fable 5 is Now Generally Available on Google Cloud! 🚀

Good news for Claude devs deploying on Google Cloud. Claude Fable 5, Anthropic’s latest frontier...

Build a Realtime Translation App with Gemini Live API, LiveKit, & Google Cloud Run

Imagine speaking in English, and having listeners from all over the world hear you translated into...

From Dashboards to Autonomous Action: Why You Need to Attend Google Cloud Labs

The era of passive data analytics is over. Today, the most forward-thinking data teams aren't just...

TanStack Start Is Kind of a Big Deal

Introduction People keep telling me TanStack Start is kind of a big deal, and I wanted to...

It's Time We All Eat some more Cucumber!

Everyone's writing specs for AI now. We hand the model a markdown file, tell it what we want, and...

You’re a Real TypeScript Developer Only If...

A few months ago, I published You're a Real JavaScript Developer Only If... It was just a post for...

I tried to make an AI agent answer more. It answered less.

If you build or evaluate scoped agents: any talk about the agent in your test context makes it defend...

Magnificent Humanity, Building Cities, and a Special Announcement!

I'm back from a great vacation and side-quest experience in Asia, where one can always find brilliant...

Introducing Gemma 4 12B: a unified, encoder-free multimodal model

Gemma 4 12B is designed to bring high-performance multimodal intelligence directly to your laptop,...

AI Won't Replace Humans — It'll Just Make Us Pickier

Every few weeks someone posts the same screenshot: an AI writing a whole app from a one-line prompt,...

Dystopian Civilization Scenarios

Gaming, like AI, is far from what fascinates me most about technology and creative development....

Retour sur le Google I/O 2026 | Focus Antigravity 2.0

En mai, la très attendue conférence Google I/O a eu lieu et le mot d’ordre, et ce n’est pas trop une...

Seamless scaling with VPA In-place Pod Resize on GKE

Learn how VPA In-place Pod Resize can help seamlessly vertically scale workloads on Google Kubernetes Engine (GKE).

I Finished What I Started: Adding AI to Every Layer of a Form Builder (With GitHub Copilot)

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built Dculus...

Winner Announcement Delayed for the Google I/O 2026 Writing Challenge

Hey all, we have a quick update for everyone who participated in the Google I/O Writing...

Agent Factory Recap: Building with Gemini 3, AI Studio, Antigravity, and Nano Banana

Welcome back to The Agent Factory! This week, we went beyond the hype to dissect the technical...

Physics, Engineering, and Architecture in Software Systems and the obsession with Architecture

Something that has been bothering me for a while in the software industry is how disproportionately...

LiveKnowledge: Engineering Verifiable Knowledge

LiveKnowledge is a CLI tool that closes the loop between unstructured text and structured, verifiable...

Extending a MCP/A2A Currency Agent with A2UI

Building an Agent with A2A, MCP, ADK, and A2UI This tutorial aims to extend and test a...

Join the June Solstice Game Jam: $1,000 in prizes!

We're excited to kick off the June Solstice Game Jam, running from June 3 through June 21 and ending...

Want to work with me? We're hiring a Community Program Manager at DEV!

Hey friends 👋 As the title suggests, we are hiring! If you've been with us for a little while, I'm...

Am I Becoming Too Slow for the AI World?

The AI world is full of old infrastructure with stochastic organs. That sentence probably explains...

Every tool seems to have a coding agent horned in these days..... I don't think that makes sense.

A post by Ben Halpern

What I'm building, and why

Two OSS dev tools shipped this month — tracelane (self-contained test-failure replays) and peek (your browser, exposed to your AI agent over MCP). Both offline, no SaaS. This is the why.

Executing Google Apps Script on Complex Schedules using Vibe Coding

Abstract Configuring complex time-driven triggers in Google Apps Script—such as...

After 7 Next.js 16 Caching Bugs, I Stopped Guessing and Built a System

There's a specific feeling you get after your third production caching incident. It's not panic....

Surviving the eviction: How to build interrupt-resilient AI workloads on GKE

Learn strategies for building interrupt-resilient AI workloads on Google Kubernetes Engine (GKE).

Top 7 Featured DEV Posts of the Week

Welcome to this week's Top 7, where the DEV editorial team handpicks their favorite posts from the...

Send your first AI message in one API call

Most AI tutorials start with a setup checklist. Pick a model provider. Create an account. Wire up a...

How we turned the Replay keynote surprise into an open-source embedded playground

We handed out 2,000 tiny hackable computers at Replay. Now the whole ecosystem is open source. Here's the story of how we built and shipped them.

Learning Lessons from Gaming

I don't identify as a gamer. I occasionally participate in board games or an amateur football match,...

Sovereign Synapse: The Context-Cleaner

(Curation is Sovereignty) Sovereign Synapse Series | Post 2 AI is polite by design. It...

Gubernator [the kill ku8s]

Why I built an alternative to Kubernetes overkill. Let’s talk about infrastructure...

Getting started with WebGPU

Learn the basics of WebGPU for modern graphics on the web.

I Used My Last 7% of Copilot Tokens to Bring a 2014 WinForms Game Back to Life

This is a submission for the GitHub Finish-Up-A-Thon Challenge Originally, I didn't plan to join...

Debloating The AI-Grown Codebase

The use of AI Agents creates a distinctive smell... One can tell the GH Repo owner was high on...

Full Field Test

ex

XSS_T1

ex1

FinalProof

no-auth

1

123

[object Object]

cttest

SrcXSS

e

SSRFTest

'"`

xtra

JSONTest

j

PP1

SRC_T

ex

Unauthorized Article Injection PoC

created without auth

<b>zzmark</b>

<i>ee</i>

t