Michelle Pokrass
7 statements across 2 episodes · 0 bullish · 4 bearish · 1 people on the record · first statement Sep 17, 2024 by Michelle Pokrass · said 3 times in 3 episodes since 2024 · across every show →
On the record as a speaker too: Michelle Pokrass's record, appearances and statements → this page counts the times other people say the name.
Mentions by year
brought up most by Alessio Fanelli (1)
tap a year for its mentions
2025 1 mention in 1 episode
2024 2 mentions in 2 episodes 1 per episode
Everything said about Michelle Pokrass, oldest first
Sep 17, 2024
Sep 17, 2024 negative
Function calling benchmarks like BFCL are largely saturated
“I find that a lot of these evals are mostly saturated, like for BFCL. All the models are near, near the top. Already. And kind of the errors are more, I would say like just differences in default behaviors. I think most of the models on the leaderboard can kin…”
Apr 15, 2025 negative
Apr 15, 2025 neutral
OpenAI uses its own models to categorize anonymized developer prompts
“Well, I will say we do use our own products internally where we can, and so we're not manually by hand reading every prompt. After they're like anonymized, we scrub them with any identifying data, then we use our models to take passes to categorize them.”
Apr 15, 2025 negative
Apr 15, 2025
GPT-4.1's multimodal vision improvements stem from pre-training, not post-training
“We talked about like coding instruction following long context, a lot of gains coming from post training, but in particular multimodal, like basically everything you're seeing, the gains are there from pre-training.”