Pavel Izmailov
7 statements across 1 episodes · 2 bullish · 0 bearish · 1 people on the record · first statement Jan 15, 2026 by Pavel Izmailov · across every show →
On the record as a speaker too: Pavel Izmailov's record, appearances and statements → this page counts the times other people say the name.
Everything said about Pavel Izmailov, oldest first
Jan 15, 2026 neutral
Izmailov: Neural network operations may not be explainable in human terms
“We want to understand it at a lower level, and it is very possible that that's just not fully possible. Like, it is some computational process that leads to some results. It doesn't have to be the case that you can Kind of describe it in human terms and kind o…”
Jan 15, 2026 positive
Izmailov: Large-scale RL has not produced coherently misaligned models
“A lot of people were worried that with large-scale RL, we will have Some completely new types of issues with the models, like this kind of coherent misalignment that will just emerge where the models are evil in some ways across many scenarios. And we are not …”
Jan 15, 2026 neutral
Jan 15, 2026
Jan 15, 2026
Izmailov: AI researchers cannot reliably trace model behaviors to pre-training sources
“We don't really know what's the source of this type of behaviors, but that's also true for a lot of other behaviors in the models with, like, even the good ones. We don't really, we cannot always pin down, like, where they come from in the pre-training.”
Jan 15, 2026
Izmailov: Text data carries more structural information per token than images
“So for example, we can approximate it from the scaling laws and we can, for example, say that text data has more structural information according to this measure than image data at the same kind of amount of yeah, tokens.”
Jan 15, 2026 positive
Izmailov: Interpretability tools are growing more useful internally at Anthropic
“So we are still pretty far from the dream that we will Fully understand everything that happens in the model, but these tools are becoming increasingly more useful internally at Anthropic in particular, and also there is constant progress, and it's pretty fasc…”