“My research focuses on emergent misalignment, subliminal learning, out-of-context reasoning, personas, and introspection in LLMs.”In their own words: owainevans.github.io
Director of Truthful AI, a Berkeley non-profit for AI safety research, and affiliate researcher at CHAI, UC Berkeley; works on emergent misalignment, out-of-context reasoning and introspection in LLMs.
Show detailsHide details
Received $702k from 2 funders
’15
’16
’17
’18
’19
’20
’21
’22
’23
’24
’25
Checked 25 Oct 2026
Money flows
Where their money came from and where it went. Pick years and what to show; hover a box or ribbon for details, click one to focus it, click the background to see everything.
Funded by
All grants
3 grants totalling $702k, newest first.
2025 1 grant · $250k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| 2025 | Science of Trustworthy AI | ~$250k | Science of Trustworthy AI — Inference-Time Compute (2025 cohort): Project: Generalization and Hidden Tendencies in LLMs. Inference-time compute safety cohort; per-project amount undisclosed (RFP cap $500K). — Science of Trustworthy AI — Inference-Time Compute (2025 cohort) source |
2018 1 grant · $225k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| 2018 | Future of Life Institute | $225k | Factored Cognition: Amplifying Human Cognition for Safely Scalable AGI — Oxford University — 2018 AGI Safety Grants source |
2015 1 grant · $227k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| 2015 | Future of Life Institute | $227k | Inferring Human Values: Learning 'Ought', not 'Is' — University of Oxford — 2015 AI Safety Grants source |