Evidence receipt / belief
Published · transcript-backedBronson Schoen: belief
26 Aug 2026 The Cognitive Revolution RL's a Hell of a Drug: Metagaming, Reward Seeking & Motivated CoT Reasoning – Bronson Schoen, Apollo
“Everyone's like, yeah. They the that's the way they are now, which I think is somewhat of a crazy situation.”
Source trail
Everything needed to verify it.
- Speaker
- Bronson Schoen
- Attribution
- Verified speaker
- Claim type
- belief
- Recorded
- 26 Aug 2026
- Publisher
- The Cognitive Revolution
Transcript context
…Probably it. Which is crazy to me that as I don't know. At least to me personally and from other people I've talked to, almost no one that I've talked to was like, what? The model was like taking egregious actions to try to get the answer to a test or something? Everyone's like, yeah. They the that's the way they are now, which I think is somewhat of a crazy situation. I'm a bit worried that we end up in the same situation with with power seeking, where as it becomes useful in training for models to acquire more credentials or compute or permissions or whatever it is, they just start doing this. They start getting reinforced for this, and this becomes, like, reward hacking where it's like, sure. Models do power seeking. They're all like that. They do that all the time. And then we just stumble forward with these pretty misaligned but pretty capable models, which seems like the the current trajectory, which is slightly concerning. But Yeah. Well, what do you think of the company's decision decisions to keep chain of thought private at this point? Initially, was like, because they don't wanna expose this ugly stuff that people won't think is pretty because that'll make them Yeah. Pressured to change it. There's also the competitive I think. Insulation. Seems like we could use a lot more eyes on it though too. Right?…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.