person
Bo Li
UChicago / UIUC; AI safety evaluations
University of Chicago associate professor specializing in safety, robustness, and trustworthiness of ML systems. Lead developer of DecodingTrust, a comprehensive trustworthiness benchmark for LLMs.
current Associate Professor of Computer Science, University of Chicago; Co-founder, Virtue AI
Strategy positions
Evals-drivenendorses
Capability/risk evals gate deployment; evals are the load-bearing artefactArgues comprehensive multi-dimensional safety benchmarks, covering toxicity, fairness, privacy, robustness, ethics, are needed to characterize AI risks empirically before deployment.
“Despite the impressive capabilities of GPT-4, we identify significant trustworthiness gaps in dimensions including toxicity, stereotype bias, robustness, privacy, and ethics.”
Closest strategy neighbours
by jaccard overlapOther people whose strategy tags overlap with Bo Li's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.
Record last updated 2026-04-25.