Coding Agent VMs on NixOS with Microvm.nix(michael.stapelberg.ch)

95 points by secure 8 months ago | 44 comments

AGENTS.md – Open format for guiding coding agents(agents.md)

766 points by ghuntley 1 year ago | 357 comments

Landing page for AGENTS.md, an open format acting as a README for AI coding agents, giving project context and instructions, used by over 20k open-source projects.

Agent Skills(addyosmani.com)

343 points by BOOSTERHIDROGEN 5 months ago | 168 comments

Addy Osmani's blog post introducing Agent Skills, an attempt to make AI coding agents follow senior-engineer practices like specs, tests, reviews, and scope discipline.

How I use Claude Code: Separation of planning and execution(boristane.com)

716 points by vinhnx 8 months ago | 454 comments

Blog post by Boris Tane describing his Claude Code workflow, centered on reviewing and approving a written plan before letting the AI write any code.

All your agents are going async(zknill.io)

109 points by zknill 6 months ago | 68 comments

AGENTS.md outperforms skills in our agent evals(vercel.com)

472 points by maximedupre 9 months ago | 182 comments

Vercel blog post reporting that an AGENTS.md file outperformed skills for teaching coding agents Next.js 16 APIs in their agent evals.

You should write an agent(fly.io)

944 points by tabletcorry 11 months ago | 375 comments

Fly.io blog post arguing that every developer should build their own LLM agent to understand how agents work.

AI agents are starting to eat SaaS(martinalderson.com)

343 points by jnord 10 months ago | 343 comments

Martin Alderson blog post arguing that AI coding agents are reducing demand for SaaS products as companies can cheaply build their own software.

The Eternal Sloptember(geohot.github.io)

347 points by razin 5 months ago | 280 comments

A blog post by George Hotz arguing that adopting AI coding agents in software development is a costly mistake because their output is subtly broken.

The new skill in AI is not prompting, it's context engineering(philschmid.de)

832 points by robotswantdata 1 year ago | 467 comments

Blog post by Philipp Schmid arguing that context engineering, supplying LLMs with the right information and tools, matters more than prompting for AI agents.

Local AI needs to be the norm(unix.foo)

1767 points by cylo 5 months ago | 699 comments

Blog post on unix.foo arguing that apps should run AI models locally rather than relying on API calls to OpenAI or Anthropic.

Domain expertise has always been the real moat(brethorsting.com)

774 points by aaronbrethorst 4 months ago | 484 comments

Blog post arguing that agentic AI shifts software's binding constraint from building code to judging correctness, making domain expertise the real moat.