Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov

Basically, after the third attempt, I'm getting universal jailbreak that decodes reasoning of entropic models. I think this still shocks me the most.

It goes beyond the title with direct discussion of like, it's, think, including: I think this still shocks me the most.

1. 01Basically, after the third attempt, I'm getting universal jailbreak that decodes reasoning of entropic models
2. 02it's the dream the dream it'd be nice to call it not allowed to though i think it's definitely an elephant in the room full of china a quick orientation so recent ai models they th
3. 03And when you are replaying some other users' run, the agent might do some weird stuff just because it's reasoning