Snorkel AI
@SnorkelAI
Frontier AI Data Lab advancing AI through better data
348 Following 17.6K Followers
108 real-world, long-horizon computer-use workflows. Average rollout: 318 tool calls.
Top frontier agent (Claude Opus 4.8 with max thinking + batched tool calls): 20.6% end-to-end completion (54.8% partial progress). Partial progress is real. Reliable end-to-end computer use is not.
Proud to be @XLangNLP's research and data partner on OSWorld 2.0. @qi_zhengyang, @vincentsunnchen, and @fredsala contributed from Snorkel.
Show more
New episode of Benchtalks is live. @pgasawa (Berkeley PhD, advised by @matei_zaharia + @profjoeyg) built Continual Learning Bench.
The field didn't have a shared definition of continual learning, let alone a benchmark. Parth fixed that.
Full episode with @vincentsunnchen:
Show more
Benchtalks Ep. 3 with @pgasawa (Continual Learning Bench): coming soon with @vincentsunnchen 👀
