Re:We tasked Opus 4.6 using agent teams to build a C Compiler
by Calavar on Thursday February 05, 2026 @08:34PM
(#46907897)
Sure, maybe it's tricky to coerce an LLM into spitting out a near verbatim copy of prior data, but that's orthoginal to whether or not the data to create a near verbatim copy exists in the model weights.
[ Parent
| on HN ]
Re:We tasked Opus 4.6 using agent teams to build a C Compiler
by D-Machine on Thursday February 05, 2026 @09:31PM
(#46908285)
Especially since the recalls achieved in the paper are 96% (based on block largest-common substring approaches), the effort of extraction is utterly irrelevant.
Re:We tasked Opus 4.6 using agent teams to build a C Compiler
by Paradigma11 on Friday February 06, 2026 @01:02PM
(#46916025)
Like with those chimpanzees creating Shakespeare.