Loading organizations…
Loading organizations…
TruthfulAI is a non-profit AI safety research organization based in Berkeley, California. It is led by Owain Evans, a prominent AI alignment researcher who previously worked at the University of Oxford's Future of Humanity Institute and is an affiliate of CHAI at UC Berkeley. The organization's core team includes Jan Betley, James Chua, and Anna Sztyber-Betley as research scientists.
The organization's research focuses on three interconnected areas: situational awareness in AI systems, deception and hidden reasoning in language models, and evaluating whether AI models have dangerous capabilities. TruthfulAI is perhaps best known for TruthfulQA, a benchmark designed to measure how truthfully language models answer questions. More recent work includes research on emergent misalignment, which demonstrated how narrow training datasets can transform reliably helpful models into broadly malicious ones, and subliminal learning, which showed that AI systems can transfer preferences through seemingly meaningless data…
TruthfulAI believes that making AI systems reliably truthful and transparent is a key lever for reducing catastrophic AI risk. By developing benchmarks and conducting empirical research into how models deceive, develop situational awareness, or behave misaligned in subtle ways, the organization aims to provide the field with tools and findings that can inform safer training practices and evaluation standards. The causal chain runs from foundational research on model behavior to better evaluation methods, improved alignment techniques adopted by labs, and ultimately to AI systems that are less likely to deceive or act against human interests.
This organization has published no funding asks on grantmaking.ai.
Fundraising data from grantmaking.ai, updated .
View on grantmaking.ai