Front-end antics and typographic mischievousness
Coding After Coders: The End of Computer Programming as We Know It - …
archived 16 Mar 2026 15:14:04 UTC
Coding After Coders: The End of Computer Programming as We Know It
In the era of A.I. agents, many Silicon Valley programmers are now barely programming. Instead, what they’re doing is deeply, deeply weird.
How creatives and devs can all finally escape the control of the silicon valley of evil and make a trillion dollars - Multi-hyphenate
ft. ATprotocol (the remix)
A programmer's loss of identity - ratfactor
This is the follow-up to last year’s I’m an American software developer and the "broligarchs" don’t speak for me. In that essay, I tried to express why I was so agonized by the leaders in my industry doing a speedrun towards dystopia and how it all felt so divorced from what technology could, and should be. Everything I wrote there is still true, but amplified.
Vibe Coding Failures: Documented AI Code Incidents
A curated directory of real-world incidents where AI-generated code failed in production.
Reading Code Is Hard, and tips to improve - Trisha Gee
This week's video for Dave Farley's Continuous Delivery YouTube channel is me ranting about why reading code sucks, and offering some advice on how to improve. "Every programmer occasionally, when nobody’s home, turns off the lights, pours a glass of scotch, puts on some light German electronica, and opens up a file on their computer. ... Read more
How creatives and devs can all finally escape the control of the silicon valley of evil and make a trillion dollars · Multi-hyphenate
ft. ATprotocol (the remix)
An Ode to Links
Writing about the big beautiful mess that is making things for the world wide web.
Cognition | Agent Trace: Capturing the Context Graph of Code
We’re excited to join in Cursor, Cloudflare, Vercel, git-ai, OpenCode and others in support of [Agent Trace](https://agent-trace.dev/). As described in the spec, Agent Trace is an open, vendor-neutral spec for recording AI contributions alongside human authorship in version-controlled codebases.
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...
Script Wizards
A TTRPG and software studio. Small tools for running games, and a zine for hackers who play them.
Prompting Claude Opus 5.5
Behavioral differences from Claude Opus 5 and the prompting and harness patterns that address them: effort calibration, thinking behavior in API integrations and chat, progress updates, unattended and multiagent tasks, safeguard refusals, frontend design, complex visual inputs, multi-app workflows, and pasted text in user messages.