Albert
@AlbertSYue
Followers
14
Following
6
Media
0
Statuses
3
Joined August 2024
Or as Llama might put it… feelings are complex and have been omitted for brevity.
0
1
1
HARD-Math is out! Was a blast working on this with y’all @Aaditya6284 @louvishh @ted_moskovitz @djstrouse .Excited to see how fast LLMs saturate on this 😝.
Math reasoning benchmarks keep getting saturated…. Excited to introduce HARD-Math: Human-Annotated Reasoning Dataset for Math. Consisting of 4,780 short answer problems, based on the AHSME, AMC, & AIME contests, HARD-Math still poses a challenge for frontier LLMs. Read on 🔎⏬
1
1
7