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 there is definitely some stuff you can think, like, on architectural side.”
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
…How is that even a thing? That's a good question you asked. It's the same people. Same people are doing the same things. Do do you think this is a structural issue? Can we fix this? I think there is definitely some stuff you can think, like, on architectural side. I mean, fairly different level of mitigations. I think they all can do some sort of revision of architecture. They can do system level mitigations, like, you know, some safeguards around this. They can do model level mitigations like we do with Shell breaks already. So, yeah, it can be mitigated to some extent. Okay. So but taking a step back, so have you stolen the models? Stolen what? Models. No. We didn't. So what have we stolen? What what is possible now that we've stolen stolen the thoughts, reasoning? Is it fair to call it thoughts? We didn't steal anything. Right? So…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.