Alex Makelov
amakelov.bsky.social
Mechanistic interpretability Creator of https://github.com/amakelov/mandala prev. Harvard/MIT machine learning, theoretical computer science, competition math.
👤 Joined on 19 November 2024
509
Followers
94
Following
17
Total Posts
📜 Kullanıcı Geçmişi
- 19 Kas 2024, 01:16
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@amakelov.bsky.social
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
Did you know I write very short essays now peligrietzer.substack.com/p/on-for-the...
Show PostToday we launch a new open research community It is called ARBOR: arborproject.github.io/ please join us. bsky.app/profile/ajy...
Show PostI got interested in philosophy because I wanted to learn how to characterize my various liminal, hypnogogic, poetic, psychedelic-ish experiences but every philosopher who actually tries super annoys me
Show PostI love imagining jokes people in very specific contexts could be making, like gay League of Legends players making jokes about a top shortage or cottage cheese producers making jokes about being a cottage industry
Show Post
« appending "Wait" multiple times to the model's generation » is our current most likely path to AGI :) See the fresh arxiv.org/abs/2501.19393 by Niklas Muennighoff et al.
Show Post