Co-author of Talkie project; formerly at Anthropic; contributing to research on vintage language models and AI generalization.
Based on 4 scored articles
Referenced in coverage
“Signed a public letter on AI safety and embedded evaluations.”
“Co-authored talkie, a vintage language model project studying AI capabilities and generalization using historical text.”
“Co-author of Anthropic study on disempowerment patterns in real-world LLM usage”
“Co-led research team that created talkie, a vintage language model with knowledge cutoff of December 31, 1930.”