⚡️Jailbreaking AGI: Pliny the Liberator & John V on Red Teaming, BT6, and the Future of AI Security

Gives a firsthand view of how practiced jailbreakers probe frontier models, which informs threat modeling and red-team practice for anyone deploying agents.

• red teaming — Deliberately attacking your own AI system to find what makes it fail before someone else does.

• videoThe State of Reasoning — from Nathan Lambert, Interconnects/AI2 [LS Live @ NeurIPS 2024]
• video⚡️ARC-AGI-3: The Interactive Reasoning Benchmark
• videoThe Agents Economy Backbone - with Emily Glassberg Sands, Head of Data & AI at Stripe
• videoOne Year of MCP — with David Soria Parria and AAIF leads from OpenAI, Goose, Linux Foundation

• video⚡️OpenCode: Claude Code but Open Source, with Any Model, and frontier TUI - with Dax Reed (@thdxr)Latent Space
• videoAnthropic’s Felix Rieseberg on AI Coworkers, Local-First Agents, and the Future of Knowledge WorkLatent Space
• videoCline: The Collaborative AI CoderLatent Space

Checking sign-in…

Loading comments…