AI can't even run a vending machine -- Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents
davel [he/him] @ davel @lemmy.ml Posts 272Comments 6,104Joined 2 yr. ago
![davel [he/him]](https://lemmy.ml/pictrs/image/a6f7fe29-6f9a-46df-a4b8-ca4390741012.jpeg?format=webp&thumbnail=128)
davel [he/him] @ davel @lemmy.ml
Posts
272
Comments
6,104
Joined
2 yr. ago
Screwdrivers can’t even hammer nails.