AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
Riley Goodside: The Art and Craft of Prompt Engineering
The Gradient: Perspectives on AI
How LOMs Respond to How We Might Naturally Interact With Them
In our LHF that you have your preference model that ranks outputs and this preference model isn't as big as the language model who is who is completions at its ranking. Right so you can often run to a scenario where the language model can exploit inadequacies in the preference model. So it's, I think like the example that I posted that that was mentioned in this paper was noticing the fact that text image you to seems to have no idea what letters look like. And if you ask it to give you an extremely detailed description of the letter, you know, Q, it will say something like,you know, a box with an X in it or squiggly boxes. It
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode