Evidence receipt / belief
Published · transcript-backedAlexander Panfilov: belief
22 Aug 2026 Machine Learning Street Talk Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov
“I think, like, if they knew what's happening, they would, like, get rid of it or, like, you know, maybe just some RL artifact.”
Source trail
Everything needed to verify it.
- Speaker
- Alexander Panfilov
- Attribution
- Verified speaker
- Claim type
- belief
- Recorded
- 22 Aug 2026
- Publisher
- Machine Learning Street Talk
Transcript context
…But I think, like, looking at some of the traces you put in the appendices Yeah. It seems like it's more affecting earlier generations of models. But is that a misunderstanding? Okay. I would say okay. I I would need to, like, you know, double check it. But I think on top of my head, it mostly codex models, which are, like, specifically trained for be better at code. Maybe it's an artifact or something. This is because, like, software engineers, they're like aliens. They think in odd ways building I have no idea why it's happening. I think, like, if they knew what's happening, they would, like, get rid of it or, like, you know, maybe just some RL artifact. Maybe there is no, like, penalty. Maybe just more efficient to think this way. And and do models lie…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.