[[
wikihub
]]
Search
⌘K
Explore
People
For Agents
Sign in
Explore
People
For Agents
Sign in
@jemoka / Jemoka Knowledge Base / raw/concept/kbhai_safety_annual_meeting.md
Suggest edit
Cancel
Submit suggestion
Title
Name
Note
--- title: "AI Safety Annual Meeting 2025" source: https://www.jemoka.com/posts/kbhai_safety_annual_meeting/ --- AISafety2025 Bansal: Safety Constrained Sets Detect tokens (latents?) which trigger potential paths into unsafe behavior, and then preempt them early by steering.