Wow, I just asked it about the details of a fairly obscure 11-citation paper of mine from 2024 and it has memorised ~all the technical details and could give a sentence-for-sentence paraphrase of large chunks of the paper. Strange experience, I recommend people try it out with their own obscure writings.
I know very little about frontier models. Can you explain how you know it had it memorized as opposed to its reading the paper after you asked the question?
As Erich_Grunewald says, it usually shows you when Claude has used a search tool, and in this case I told it not to use search and it didn’t show me any usage. But it was so impressive that I’m at like 10% that there’s some secret hidden search tool type thing that explains it.
Wow, I just asked it about the details of a fairly obscure 11-citation paper of mine from 2024 and it has memorised ~all the technical details and could give a sentence-for-sentence paraphrase of large chunks of the paper. Strange experience, I recommend people try it out with their own obscure writings.
I know very little about frontier models. Can you explain how you know it had it memorized as opposed to its reading the paper after you asked the question?
The Claude interface shows you when the model has searched the web for information.
Thanks. (I haven’t tried Claude because I don’t have a mobile phone, which Claude requires for sign-up.)
As Erich_Grunewald says, it usually shows you when Claude has used a search tool, and in this case I told it not to use search and it didn’t show me any usage. But it was so impressive that I’m at like 10% that there’s some secret hidden search tool type thing that explains it.