Go starts at $5 for your first month, then $10/month, with generous 5-hour request limits for GLM-5.1, GLM-5, Kimi K2.5, Kimi K2.6, MiMo-V2.5-Pro, MiMo-V2.5, Qwen3.7 Max, Qwen3.6 Plus, MiniMax M2.5, MiniMax M2.7, MiniMax M3, DeepSeek V4 Pro, and DeepSeek V4 Flash.
Running local models is good now
Local agentic coding has gotten great over the past few months
Vibe-coded Go static analysis tools
Ideas are now a major bottleneck for vibe-coding. There are whole categories of software that simply don’t occur to me to write. Philip Zeyliger pointed me at one: Go static analysis tools. These are great candidates: easy to describe easy to test high value low risk He created a checker that requires slog.InfoContext instead of slog.Info when a context is available, to improve our telemetry/observability. I followed up with a checker that lets you annotate a Go struct as requiring complete, explicit annotation.
GLM-OCR Technical Report
GLM-OCR is an efficient 0.9B-parameter compact multimodal model designed for real-world document understanding. It combines a 0.4B-parameter CogViT visual encoder with a 0.5B-parameter GLM...
AI costs how much? GitHub Copilot users react to new usage-based pricing system.
Some report burning through their whole monthly "AI credit" allotment in a single day.
Open Source Barcode Generator
Zint is a free and open-source barcode generator for desktop, command line and developer workflows, supporting many linear, stacked, postal and matrix barcode formats.
You can code only 4 hours per day. Here’s why.
Most of us have felt it: after a few solid hours of coding, your brain starts shutting down.
Astra for Coding: Why Are We Doing This Again?
Some thoughts on Astra and newfangled long-horizon models.
Amazon seeks cheaper AI alternatives as Anthropic shifts to token-based pricing
Amazon is exploring OpenAI as an alternative to Claude after a renegotiated contract with Anthropic will raise costs through token-based pricing.
Don't couple your Go code to GitHub | Iain Cambridge
The technical musings of Iain Cambridge.
Learn Go by Building a Command Line Todo App | Barbarian Meets Coding
Learn the Go programming language by building a test-driven command line todo application
Note on 24th September 2026
The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder. We can do amazing things with them, but unlocking …
Magicoder: Empowering Code Generation with OSS-Instruct
We introduce Magicoder, a series of fully open-source (code, weights, and data) Large Language Models (LLMs) for code that significantly closes the gap with top code models while having no more...
PrimeIntellect-ai/prime-agent
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Review the reviews
When I was actively contributing to the Go project, my primary feed was the code review email firehose. Issues, mailing lists, and Slack had low SNR. The finished commit history was better: it was finely polished work with some of the best written commit messages I have ever encountered. But it didn’t hold a candle to code reviews for operational learning. The commit history could tell you what got done and why, in impressive technical detail.
CodePen 2.0
Noting perhaps my largest personal career accomplishment, which is launching CodePen 2.0. Far more work, believe it or not, than the entire creation of the original CodePen. This isn’t the pl…
✨🙌 AI that helps communities thrive on their own terms
Open protocols + AI-enabled coding = building what we need for ourselves
