Izmailov: Deterministic data transformations create information for computationally bounded models
Pavel Izmailov · The Evaluators Are Being Evaluated — Pavel Izmailov (Anthropic/NYU) · Jan 15, 2026 · at 35:37
Pavel Izmailov (Anthropic/NYU) explains the core thesis of his paper on epiplexity, challenging classical information theory views on synthetic data.
0:00 / 0:09exact quote · 9.3s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“But with a limit on the compute, it's actually very possible to apply deterministic transformations to the data. And create information through that.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Pavel Izmailov
Izmailov: Anthropic has a better corporate culture than OpenAI and xAI
“In my mind, Antropic has the best culture of the three places.”
Izmailov: AI sabotage and blackmail behaviors require contrived research scenarios
“In order to get those behaviors out of the models, you need to create somewhat of a contrived scenario or some special scenario. It's not necessarily something that we observe normally.”
Izmailov: Current AI models lack continual learning and cross-setting coherent goals
“I am pretty confident we are not there at the moment. I think right now the models are still acting in isolated environments, and we are not seeing a lot of evidence for very coherent goals across different settings”
Izmailov: Rogue AI science fiction in training data likely causes deceptive behavior
“I think at least part of it is probably The models seeing descriptions of AI, like in the science fiction literature going rogue and like, yeah, that probably affects how the models behave in similar scenarios.”
Izmailov: AI industry excels at execution but lacks bandwidth for exploration
“Industry is really great at executing on ideas and it's maybe not as good at, like, exploring diverse ideas. Even at the scale of Anthropic OpenAI there is a lot of focus in the companies, and there isn't a lot of bandwidth to do exploration, and that has been…”