This episode features Zico Kolter and Matt Fredrikson from Grey Swan discussing AI security challenges, particularly around adversarial attacks and indirect prompt injection in large language models and AI agents. They explain their approac…
Firehose
Filtered to tagged “Mechanistic interpretability” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
artificial intelligence 63open-weight models 19agentic coding 17continual learning 16AI 15AI agents 11reinforcement learning 9datasette 8AI safety 7cybersecurity 7Databricks 7natural language processing 7AI Gateway 6large language models 6Reinforcement learning 6vision-language models 6computer vision 5Diffusion models 5language models 5machine learning 5open-source 5Agentic AI 4AI ethics 4benchmarks 4education 4productivity 4recursive self-improvement 4Recursive self-improvement 4space 4tech 4
This episode features Biohub co-founders Mark Zuckerberg and Priscilla Chan, along with Head of Science Alex Rives, discussing their ambitious goal to cure, prevent, and manage all disease by the century's end, now accelerated by AI. They d…
Alex Rives, Head of Science at Biohub, discusses ESM-C, a fourth-generation protein language model that leverages the "Bitter Lesson" of scaling with massive metagenomic datasets to achieve unprecedented protein structure prediction and des…