A sufficiently detailed spec is code(haskellforall.com)

535 points by signa11 7 months ago | 291 comments

A Haskell for all blog post, built around a comic strip, arguing that a specification detailed enough to generate a program is effectively code itself.

Show HN: Huzzah – a novel approach to coding with AI(danielvaughn.dev)

334 points by danielvaughn 2 months ago | 178 comments

Blog post introducing Huzzah, an experimental editor where you write pseudocode that is synced to real source code by AI on save, with the pseudocode kept as intent.

Figma's woes compound with Claude Design(martinalderson.com)

80 points by martinald 6 months ago | 70 comments

Coding Is Hard(duttakapil.com)

68 points by duttakapil 2 years ago | 93 comments

No, it doesn't cost Anthropic $5k per Claude Code user(martinalderson.com)

401 points by jnord 7 months ago | 292 comments

Blog post by Martin Alderson rebutting a Forbes claim that Anthropic's $200/month Claude Code Max plan consumes $5,000 in compute per user.

Abusing DuckDB-WASM by making SQL draw 3D graphics (Sort Of)(hey.earth)

183 points by tanelpoder 1 year ago | 31 comments

Coding expertise is going to collapse from AI reliance(larsfaye.com)

490 points by larsfaye 2 months ago | 479 comments

Blog essay by Lars Faye arguing that reliance on AI coding tools removes the friction needed to develop long-term programming expertise.

We mourn our craft(nolanlawson.com)

634 points by ColinWright 8 months ago | 737 comments

Nolan Lawson's blog post lamenting how AI coding tools are reducing programmers to code reviewers and mourning the loss of the programming craft.

Prevent cognitive debt by manually retyping LLM-generated code(ankursethi.com)

502 points by mpweiher 2 months ago | 413 comments

A personal blog post arguing that developers should manually retype code generated by LLM coding assistants to keep understanding it and avoid cognitive debt.

Lines of code got a better publicist(curlewis.co.nz)

417 points by RyeCombinator 4 months ago | 288 comments

A blog post by David Curlewis arguing that AI-era productivity metrics are repackaging lines of code as a measure of developer output.

The cult of vibe coding is dogfooding run amok(bramcohen.com)

541 points by drob518 6 months ago | 454 comments

Bram Cohen blog post arguing that the leaked Claude source code's poor quality reflects vibe coding dogfooding taken to cult-like extremes.

An AI coding agent, used to write code, needs to reduce your maintenance costs(jamesshore.com)

331 points by cratermoon 5 months ago | 99 comments

James Shore blog post arguing that AI coding agents must cut software maintenance costs proportionally to how much they speed up code writing.