Evidence receipt / evaluation
Published · transcript-backedTim Scarfe: evaluation
22 Aug 2026 Machine Learning Street Talk Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov
“The right word is jailbreaking and abuse because he fears regulatory overreaction from banning Chinese built open weights model.”
Source trail
Everything needed to verify it.
- Speaker
- Tim Scarfe
- Attribution
- Verified speaker
- Claim type
- evaluation
- Recorded
- 22 Aug 2026
- Publisher
- Machine Learning Street Talk
Transcript context
…So Yeah. I think it's just we're a bit too poor compute wise. If we could properly study this, and maybe eventually we'll get to a point where we can. It's but but it definitely requires a very precise experiment. Like, as a scientist, it just feels very hard to say, no. No. No. This is exactly this is the phenomenon. That's it. No. It's very observational studies. You can't prove a hypothesis. You can only reject hypothesis. Right? Like, it's the very fundamental truth of all of this. We are just observers. So let's see. Let's see what happens. Well, apparently, Nathan Lambert said, calling this a distillation attack tarnishes all distillation. The right word is jailbreaking and abuse because he fears regulatory overreaction from banning Chinese built open weights model. Thoughts? That's definitely jailbreaking and misuse. 100%. That's exactly…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.