CoPilotBlog
1,757 blog available in the CoPilot directory
Articles, tutorials, and deep dives on this AI platform β from getting-started guides to advanced techniques and real-world use cases.
devchallengeCongrats 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,...
J
Jem 1
mlhacksCongrats 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...
J
Jem 1
discussDev 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,...
H
Hemapriya Kanagala 1
gemmaGemma 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.
X
xbill 2
weeklyretroWhat was your win this week??
ππππ Looking back on your week -- what was something you're proud of? All wins count -- big or small...
J
Jess Lee
aiStuart Feldman Was Right in 1976: Why Your AI Agent Needs a Makefile, Not a 20-Step Prompt
How replacing fragile linear prompt checklists with a 50-year-old declarative build graph eliminates agent amnesia, enables seamless mid-flight session resumption, and mechanizes software engineering governance.
R
Randal L. Schwartz 2
flutterLlama Village: a virtual world powered by local AI with llamadart
Llama Village in motion. The charactersβ dialogue is generated by an on-device model. Watch the...
J
Jhin Lee
aiI 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 itβs fast,...
S
Swift 2
gemmaGemma 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.
X
xbill
dartMaking cross-platform local AI easier with llamadart
My writing assistant could talk to Gemini. The missing piece was using it without a connection. That...
J
Jhin Lee
claudeClaude Haiku 5.5 is available on Google Cloud
Hey developers! If youβve been building autonomous agents or multi-agent orchestrations, you...
J
Jen Harvey
welcomeWelcome Thread - v 396
Leave a comment below to introduce yourself! You can talk about what brought you here, what you're...
S
Sloan the DEV Moderator
googlecloudstop-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...
R
Ruchika Goel
hackathonRun, 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...
M
Martin Omander
awsGemma 4 Inference on AWS: Bedrock, SageMaker, GPUs, Inferentia and Trainium Behind One Strands Agent
A step by step survey of six ways to serve a model on AWS, from a managed API to your own Neuron chip, driven by one Strands agent and measured on the same day with the same prompts.
X
xbill
top7Top 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...
J
Jem
arduinoBuild a Tiny Virtual Pet on Arduino in 60 Minutes πΎ
Turn an Arduino Uno Q into Kiku, a Tamagotchi-style virtual pet with an animated LED face, moods, and keyboard controls.
J
Jen Looper
databaseActivating Your Data Layer for Production-Ready AI
When discussing applications and systems using generative AI and the new opportunities they present,...
G
Gleb Otochkin
devchallengeJoin the Hacktoberfest Open-Source AI Challenge: Touch Grass! $2,450 in Prizes Across 17 Winners.
Week 1 of our five Hacktoberfest DEV Challenges starts today! Running through October 11, the...
J
Jem
substackPublishing Markdown to Substack from an Agent Skill
Substack has no publishing API, its editor has no tables, and a link around inline code is dropped on paste. A step by step walk-through of the Substack destination in publishing-kit: what the editor keeps, what it drops, and how an agent publishes to it and reads the result back.
X
xbill
discussWhy 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 that I have been holding off on my...
F
FrancisTRα΄
α΄α΄ 
claudecodeMCP Configuration for Google Workspace with Claude Code
Connect Claude Code to Google's eight remote Workspace MCP servers (Gmail, Drive, Docs, Sheets, Slides, Calendar, Chat and People), packaged as a Claude Code skill, with the two sign-in limits that decide how you use it.
X
xbill
discussMeme Monday
Meme Monday! Today's cover image comes from the last thread. DEV is an inclusive space! Humor in...
B
Ben Halpern
aiEvent-Driven AI at Cloud Scale: High-Throughput Stream Classification with Pub/Sub, Dataflow, and Jev
How to turn millions of events per hour into typed, confidence-scored decisions, without a...
S
Saurabh Mishra