Long llama is a large language model capable of handling long contexts of 256 tokens. The more information there is, the greater chance that the model will get almost distracted by irrelevant information in the input. This means essentially a whole bunch of irrelevant information, a prompt that like causes the model to get confused. And they specifically train the model using the technique called contrastive learning to explicitly figure out what is relevant and what's not relevant so it can generate its output.
Our 130th episode with a summary and discussion of last week's big AI news!
Co-hosted this week by Jon Krohn of the Super Data Science Podcast podcast.
Correction: Elon Musk's company is named xAI, not x.AI.
Read out our text newsletter and comment on the podcast at https://lastweekin.ai/
Email us your questions and feedback at contact@lastweekin.ai
Timestamps + links:
- (00:00) Intro / Banter
- (07:30) Response to listener comments / corrections
- Tools & Apps
- Applications & Business
- Projects & Open Source
- Research & Advancements
- Policy & Safety
- Synthetic Media & Art
- (01:44:20) Outro