Swyx joined SAIL! Thank you SAIL Media, Prof. Tom Yeh, 8Lee, Hamid Bagheri, c9n, and many others for tuning into SAIL Live #6 with Nathan Lambert and Sebastian Raschka, PhD. Sharing here for the LS paid subscribers.
We covered:
← The conversationsLatent Space Podcast
[LIVE] Anthropic Distillation & How Models Cheat (SWE-Bench Dead) | Nathan Lambert & Sebastian Raschka
Latent.Space x Interconnects x Ahead of AI Substack Live: SAIL Live #6
Listen to this conversation52 min
Read transcript
Thanks for reading
Stay a little ahead of the curve.
Fresh ideas, original reporting, and deep conversations in your inbox.
Subscribe to Latent SpaceGo a little deeper
The wikiSourced profiles and separately reviewed explanations connected to this post.
Grounded writeup
Distillation, borrowed answers, and the limits of SWE-bench
Why API traffic cannot easily reveal training intent, why the strongest model may be a poor teacher, and how coding benchmarks can reward knowledge their tasks never supplied.
Person
Sebastian Raschka
LLM research engineer and author whose books, code and technical essays explain language models through working implementations and practical experiments.