Loading activity…
@xdotli
evals + envs @benchflow_ai chat about evals https://discord.gg/mZ9Rc8q8W3
AI
Dream Labs says Dream-1 controls unfamiliar two-armed robots on unseen tasks, with access starting at $3 an hour.
AI
The speaker says the talk will be in San Francisco and offers a speaker code by DM.
AI
A post argues that human tasks are now too easy to use as AI benchmarks in many domains.