13min chapter

The Gradient: Perspectives on AI cover image

Sasha Rush: Building Better NLP Systems

The Gradient: Perspectives on AI

CHAPTER

Exploring Prom Tuning and Controllability in NLP Systems

The chapter delves into the speaker's work on Prom Tuning, collaboration with Hugging Face, and in-context learning in AI models. It discusses mechanistic interpretability efforts, multi-task prompted training, controllability in NLP systems, and the challenges and evolving nature of NLP tasks. The speaker reflects on methods like instruction tuning and the importance of good prompts for achieving control in model outputs while expressing skepticism towards some approaches and the need for further research in closing the gaps in NLP systems.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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