News for hackers. Stuff that matters.

A comment on We tasked Opus 4.6 using agent teams to build a C Compiler. Parent comment

Re:We tasked Opus 4.6 using agent teams to build a C Compiler by dcre on Friday February 06, 2026 @10:18PM (#46920987)
We have investigated. Millions of people are investigating all the time and finding that the coding capacity has improved dramatically over that time. A variety of very different benchmarks say the same. This one random guy’s stupid prompt says otherwise. Come on.
[ Parent | on HN ]
Re:We tasked Opus 4.6 using agent teams to build a C Compiler by thesz on Saturday February 07, 2026 @02:54AM (#46922126)
As far as I remember, article stated that he found same problematic behavior for many prompts, issued by him and his colleagues. The "stupid prompt" in article is for demonstration purposes.
[ Parent | on HN ]
Re:We tasked Opus 4.6 using agent teams to build a C Compiler by dcre on Monday February 09, 2026 @09:15AM (#46945430)
But that’s not an argument, that’s just assertion, and it’s directly contradicted by all the more rigorous attempts to do the same thing through benchmarks (public and private).
[ Parent | on HN ]