News for hackers. Stuff that matters.
Re:We tasked Opus 4.6 using agent teams to build a C Compiler by shakna on Thursday February 05, 2026 @05:07PM (#46906061)
Well, "Reimplement the c4 compiler - C in four functions" is absolutely something older models can do. Because most are trained, on that quite small product - its 20kb.

But reimplementing that isn't impressive, because its not a clean room implementation if you trained on that data, to make the model that regurgitates the effort.

Re:We tasked Opus 4.6 using agent teams to build a C Compiler by signatoremo on Thursday February 05, 2026 @06:52PM (#46907150)
> Well, "Reimplement the c4 compiler - C in four functions" is absolutely something older models can do.

Are you sure about that? Do you have some examples? The older Claude models can’t do it according to TFA.

Re:We tasked Opus 4.6 using agent teams to build a C Compiler by shakna on Thursday February 05, 2026 @11:39PM (#46909196)
Not ones I recorded. But something I threw at DeepSeek, early Claude, etc.

And the prompt was just that. Nothing detailed.