logoalt Hacker News

SwellJoe • today at 5:57 AM • 3 replies • view on HN

Anthropic needs to teach Opus how to speak English again, because Opus 5 seems to have forgotten. Utterly incoherent a lot of the time. They seem to be so busy scare-mongering and cooking up guardrails and watermarks that they haven't noticed that their models are getting weird.

Replies

aix1 • today at 7:26 AM

It still knows how to speak English. When I tell it to explain something in plain language, it generally does a very good job. The weird thing is that those instructions don't persist: it lapses back into Claude-speak pretty much every turn no matter how hard I try to instruct it not to.

(In my case "it"=Fable; I assume Opus is similar.)

➕ show 1 reply
hypfer • today at 6:11 AM

Are those watermarks why claude suddenly started being even more unbearable to work with lately?

Man. That would make a lot of sense indeed.

➕ show 1 reply
igravious • today at 8:26 AM

Amen brother, at this point I just copy and paste Claude's (Opus 5, Opus 4.8 -- doesn't matter which) summaries over to the window Kimi is in and:

   this is from claude, turn it into English for me would you?
   """
   [claude's tortuous prose]
   """
No amount of asking it to answer me in a straight-forward manner, to be succinct, to not use phrases like "honest caveat", "crux", "load-bearing", "blocker", etc ever sticks for more than a few turns … coupled with the fact that it can ignore instructions and do its own thing and then what I can only describe as lie about it using Claude can be an exercise in frustration. Kimi and GLM talk to me like a human, Luna/Terra/Sol are much better in that respect also, and Grok is marvelously structured and bullet-pointy in its explanations but unfortunately it is not as strong …
➕ show 1 reply