Because PAT is a reproducible agent, Bridgewater can use something much more dependable than vibes-based or LLM-as-judge evaluations; instead they use deterministic benchmarking and testing.
causalpending
Speaker
Santi WeightEvidence Quote
“And then because we have such a reproducible agent, as we're scaling and hill climbing and evaluating, we have something much more dependable than vibes-based or LLM-as-judge evals.”
Created: 8/12/2026, 6:15:31 PM
Your notes
Loading notes...