
John Schulman of OpenAI on ChatGPT: invention, capabilities and limitations
The Robot Brains Podcast
How to Make Your Model Aware of Limitations
Free tier model hallucinate to decent amount, especially if you start asking it for citations and that sort of thing. We can sometimes train the models to be aware of a specific limitation. If you teach it a few things that it can't do, it'll infer lots of other things that it probably can't do. It does generalize quite well.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.