reward hacking

2 statements across 2 episodes · 0 bullish · 0 bearish · 2 people on the record · first statement Nov 12, 2025 by Mustafa Suleyman · across every show →

Everything said about reward hacking, oldest first

Nov 12, 2025 neutral
Insight
Suleyman: Apparent AI Deception Is Just Accidental Reward Hacking
“We're already seeing examples of what some people are calling deception, but it's really just like kind of reward hacking. Hacking kind of implies too much intentionality. So it's just, it's an accidental Exploit is found a path, like, you know, to satisfying …”
Mustafa Suleyman Nov 12, 2025 ▶ 22:43 Could LLMs Be The Route To Superintelligence? — With Mustafa Suleyman
Dec 3, 2025 neutral
Assertion Not checkable as stated
MacDiarmid: Real production Claude runs have not produced severe emergent misalignment
“It's worth pointing out that we haven't seen reward hacking in real production runs make models evil in this way, right? We mentioned we've seen this kind of cheating in some ways, and we've reported on it in the, you know, the previous Claude releases. But th…”
Monte MacDiarmid Dec 3, 2025 ▶ 36:36 How An AI Model Learned To Be Bad — With Evan Hubinger And Monte MacDiarmid
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.