Anka Reuel ➡️ NeurIPS
ankareuel.bsky.social
Computer Science PhD Student @ Stanford | Geopolitics & Technology Fellow @ Harvard Kennedy School/Belfer | Vice Chair EU AI Code of Practice | Views are my own
👤 Joined on 25 November 2024
1280
Followers
1015
Following
68
Total Posts
📜 Kullanıcı Geçmişi
- 25 Kas 2024, 18:54
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@ankareuel.bsky.social
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
A recent Stanford paper reveals that many popular AI benchmarks are fundamentally flawed: They can be outdated, easily gamed, or inaccurate. Stanford HAI Graduate Fellow @ankareuel.bsky.social talks about how researchers are rethinking AI benchmarks: www.emergingtechbrew.com/stories/2025...
Show Post
Organizers: Ben Bucknall, @lisasoder.bsky.social, @ankareuel.bsky.social @fbarez.bsky.social, @carlosmougan.bsky.social Weiwei Pan, Siddharth Swaroop, @ankareuel.bsky.social , Robert Trager @maosbot.bsky.social
Show Post
This work was done at MATS led by Leon Staufer and Mick Yang. Great to collaborate with @ankareuel.bsky.social as well.
Show Post
oh shit, this is nice! holding an eval hackathon atm, will share! is this limited to the current paradigm of static dataset type benchmarks, or could it also work for like llm judges, environments for agents, cellular automata simulation, etc?
Show Postoh sweet, you have agentbench here, so it does. ok, will share
Show Post