When an AI writes bad code the thing to fix is the context it was given, not the code, because fixing the output adds no leverage.

Added to korrents 18 Aug 2025 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• Coding models are worst at exactly the thing an AI research explosion would need: code that has never been written before. AKAndrej Karpathy17 Oct 2025similar wording
• Forcing an AI to annotate every type would make its programs worse, not better: annotate where there is no context, and let inference do the rest. AHAnders Hejlsberg13 May 2026similar wording
• Refusing to write code with AI can be a philosophical decision rather than a productivity one: the reason to program something is that you want to program it. CMCasey Muratori26 Aug 2026similar wording
• AI writes code well only where a million repositories have already written it; getting it to do something genuinely new remains notoriously hard. TSTim Sweeney30 Apr 2025similar wording
• The meme that programmers no longer need to be competent is a trap: the path is competence, and AI does not change that. DHDavid Heinemeier Hansson18 Sept 2024similar wording

See this on the map →