AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
RLHF: A thin line between useful and lobotomized
Interconnects
Exploring Preference Alignment in Data Sets for Model Evaluation
Exploring the biases within GPT-4 and its influence on data sets used for model evaluation, alongside the role of alternative models like alpaca and vacuna. This chapter discusses credit assignment in sequences, the effects of preference alignment on model outputs, and the variations in training data due to different models.
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