#142 - Humanoid Robots, Video-To-Text, Habitat 3.0, Cruise troubles, data poisoning
Last Week in AI
00:00
The Role of Generalization in Agent Behavior
They can take a llama to a base model and fine tune it to achieve agent performance similar to GPD 3.5. Their system is impressive because it reaches a level that previous models couldn't. They can perform tasks like online shopping, web browsing, and general computer tasks. When fine tuning, they retain the general world knowledge to help the agents perform better on general reasoning tasks. This approach is different from traditional fine tuning for dialogue and instruction following.
Play episode from 01:07:30
Transcript
