Presenting
Defense Against LLM and AGI Scheming with Guardrails and Architecture
April 28 @ 6:45 pm – 8:45 pmHybrid meeting: In-person, Zoom, and YouTube Greg Makowski, Chief of Data Science at Ccube TALK DESCRIPTION A January 2025 paper called “Frontier Models are Capable of In-Context Scheming”, https://arxiv.org/pdf/2412.04984, demonstrated how a wide variety of current frontier LLM models (i.e…. Read more