causal
Agency Expands Safety Surface Area Non-Linearly
As AI models gain tool access and internet access, the surface area for things to go wrong expands, and the sophistication of required safety measures grows, creating a tension in which better models permit more agency but also demand more complex guardrails.
causalpending
Speaker
Bret TaylorEvidence Quote
“as the models get better, you can give the AI more agency to complete tasks, but I think the level of sophistication of the safety issues that you have to handle also get more broad and complex”
Created: 11/18/2026, 1:16:45 PM
Your notes
Loading notes...