AdamW

topic on 3 shows · 3 statements across 3 episodes · said 6 times in 2 episodes since 2024

Latent Space 3 the a16z Podcast 3 the MAD Podcast

Mentions by year, every show

tap a year for its mentions
00213120242025episodesmentions
01120242025episodes it came up in
001.50.53120242025episodesmentions per episode

the a16z Podcast 3Latent Space 3

2025 3 mentions in 1 episode
2024 3 mentions in 1 episode

every mention on every show, scene by scene, with the transcript →

3 statements about AdamW, every show

MAD Prediction Not checkable as stated
RLVR and GRPO will stabilize into canonical algorithms similar to AdamW
“It's similar to, you know, optimizers with Adam. So Adam is, I mean, right now there's Adam W. There was SGD and all the other RMS prop and how they were called. And they kind of all converge to Adam W by adding more and more tricks. And I think that's the sam…”
Sebastian Raschka Jan 29, 2026 ▶ 34:51 State of LLMs 2026: RLVR, GRPO, Inference Scaling — Sebastian Raschka
LATENT SPACE Assertion Not checkable as stated
Bakouch: Novel optimizer speedups are exaggerated due to undertuned AdamW baselines
“And what they find is that the speed up is greatly, greatly exaggerated. And mostly because often people like undertone the Adam W baseline.”
Elie Bakouch Oct 20, 2025 ▶ 16:06 ⚡ Open Model Pretraining Masterclass — Elie Bakouch, HuggingFace SmolLM 3, FineWeb, FinePDF
a16z Assertion Not checkable as stated
DisTrO's performance advantage over AdamW widens as models scale up
“What we have seen empirically is that as we make it bigger, the differential between distro and MW actually gets wider.”
Jeff Schmidt Oct 1, 2024 ▶ 35:35 The Quest for Community-Trained Open Source AI Models

← every entity, every show

Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.