Thread

1. hungryhobbit · 1790193542 · focus · HN ↗

   How about you make Opus 5.5 actually work?

   I had it try to prepare a code review for me. Not only did it refuse, it refused to even tell me what the prompt (written by another Claude!) was. Why?

   When I had another model read the session (all of the "stupider" models handled it just fine) it explained that it had the word "reasoning" in it

   That's the entirety of Anthropic's billions of dollars of research: any prompt with the word "reasoning" is trying to hack Claude to figure out how it reasons!

   A model like that should never have gotten out of QA, let alone been released.

   1. post-it · 1790195006 · focus · HN ↗

      > When I had another model read the session (all of the "stupider" models handled it just fine) it explained that it had the word "reasoning" in it

      Did it explain it did it hallucinate?

      1. hungryhobbit · 1790196057 · focus · HN ↗

         This happened at the classifier level, there was no "Claude thought X about it (hallucinating or otherwise)": this was a glorified regex deciding Claude couldn't work on a prompt (a code review prep) because it contained a string ("reasoning") it didn't like.

         It's more or less the same mistake we've seen Anthropic make repeatedly with it's brain-dead regex-based Fable/Mythos gates.

         1. post-it · 1790197247 · focus · HN ↗

            > because it contained a string ("reasoning") it didn't like.

            How do you know? How would the stupider model know?

            1. nfcampos · 1790198837 · focus · HN ↗

               Because it’s in a page accessible from its search tool presumably <a href="https:&#x2F;&#x2F;claude.dev&#x2F;blog&#x2F;getting-the-most-out-of-opus-5-5&#x2F;" rel="nofollow">https:&#x2F;&#x2F;claude.dev&#x2F;blog&#x2F;getting-the-most-out-of-opus-5-5&#x2F;

Unofficial Hacker News client; not affiliated with Y Combinator.