Quentin Gallouédec
@qgallouedec.hf.co did:plc:htrbf6kwqgkbqvwfdopp6wsq
PhD - Research @hf.co 🤗 TRL maintainer
Sur Bluesky depuis le
- Abonnés
- 941
- Abonnements
- 170
- Posts
- 17
- Jours dans les classements
- 0
Résumé
Quentin Gallouédec (@qgallouedec.hf.co) est sur Bluesky depuis le 18 novembre 2024. Le compte a 941 abonnés, suit 170 comptes et a publié 17 posts.
Présence dans les classements
Les meilleurs jours où les posts de ce compte sont entrés dans le top quotidien de Debya.
Ce compte n’est encore apparu dans aucun classement quotidien.
Posts aimés récemment
J’aime publics du réseau Bluesky.
What if AI becomes as ubiquitous as the internet, but runs locally and transparently on our devices? Fascinating TED talk by @thomwolf.bsky.social on open source AI and its future impact. Watch the full talk here: www.ted.com/talks/thomas...
Voir le post🧵 1/12 New blog post alert! With @mmitchell.bsky.social, @evijit.io and @sashamtl.bsky.social we talk about what appears to be one of the biggest shifts happening in AI: agents. These aren't your typical chatbots - they're systems that can take autonomous actions based on high-level goals.
Voir le postWhat are some known/published *active* applications of RL in production (i.e. are actually providing some financial utility)? Note that this excludes games, simulations, and in-lab robotics.
Voir le postWrite your training loops with care, as if your ML model hated you and wanted you to fail.
Voir le postThere's a lot of confusion about o1's RL training and the emergence of RL as a popular post-training loss function. Yes, these are the same loss functions and similar data. BUT, the amount of compute used for o1's RL training is much more in line with pretraining.
Voir le post
Comptes bloqués
Sur Bluesky, les blocages sont publics.
