News for hackers. Stuff that matters.
Re:I caught Google Gemini using my data–and then covering it up by Otter-man on Tuesday November 18, 2025 @12:46AM (#45961777)
Another model - I don't quite remember which, I think it was one of GPT ones? - didn't have access to thinking traces after it finished the thought - they simply were removed from the context to save tokens. Can it be the same with Gemini? Maybe it just doesn't know what it did/thought in the previous turn and so it hallucinates that it doesn't have context access function.

There are no comments on this comment yet.