Comment Comment by cowsaymoo The part about taking control of a reasoning model's output length using <think></think> tags is interesting.> In s1, when the LLM tries to stop thinking with "</think>", they force it to keep going by replacing it with "Wait".I had found a few days ago that this let you 'inject' your own CoT and jailbreak it easier. Maybe these are related?https://pastebin.com/G8Zzn0Lwhttps://news.ycombinator.com/item?id=42891042#42896498 parent cowsaymoo 1 year ago
> In s1, when the LLM tries to stop thinking with "</think>", they force it to keep going by replacing it with "Wait".
I had found a few days ago that this let you 'inject' your own CoT and jailbreak it easier. Maybe these are related?
https://pastebin.com/G8Zzn0Lw
https://news.ycombinator.com/item?id=42891042#42896498