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 friendzis on Friday February 06, 2026 @11:27AM (#46914882)
Because literally no real-world non-research project starts with "we have an extremely comprehensive test suite and specification complete down to the most finite detail" and then searches for a way to turn it into code.
[ Parent | on HN ]
Re:We tasked Opus 4.6 using agent teams to build a C Compiler by galdauts on Friday February 06, 2026 @12:50PM (#46915911)
Precisely. Figuring out what the specification is supposed to look like is often the hardest part.
[ Parent | on HN ]
Re:We tasked Opus 4.6 using agent teams to build a C Compiler by mastermage on Saturday February 07, 2026 @10:42AM (#46924730)
100% agreed i use Claude often to just bounce ideas back and forth on specs i would like to create which I know will never gain traction because its either way too ambitious or too niche.

And the amount of times Claude proposes something thats completely contradictory in the same response. Or completely does a 180 after two more responses. Is ridiculous.

[ Parent | on HN ]
Re:We tasked Opus 4.6 using agent teams to build a C Compiler by ryanjshaw on Friday February 06, 2026 @02:13PM (#46916879)
I’ve spent nearly 20 years working as a consultant writing software, I know that. How do you think humans solve that problem?
[ Parent | on HN ]
Re:We tasked Opus 4.6 using agent teams to build a C Compiler by friendzis on Saturday February 07, 2026 @06:38AM (#46923050)
Typically by putting cost caps on deliverables.
[ Parent | on HN ]
Re:We tasked Opus 4.6 using agent teams to build a C Compiler by ryanjshaw on Tuesday February 10, 2026 @02:16AM (#46956371)
Which is pretty much what I said once you factor in that you evaluate (test) the deliverables before paying more.
[ Parent | on HN ]