Jack Lindsey

@jack_w_lindsey

Neuroscience of AI brains @AnthropicAI. Previously neuroscience of real brains @cu_neurotheory.

More reliable readings of models’ internal signals and stronger tests of what causes their behavior top one commenter’s list of research priorities.

3 Sources, 34d ago, first seen 34d ago

Pseudonymous AI commentator @scaling01 shares views on monitoring techniques for advanced models.

37 Sources, 48d ago, first seen 48d ago

Anthropic researcher discusses mind-reading techniques and their implications for model cognition.

1 Source, 49d ago, first seen 49d ago

Jack Lindsey shares questions on instilling values and mitigating reward hacking effects.

2 Sources, 49d ago, first seen 49d ago

Jack Lindsey leads Anthropic's Model Psych team and posted the opening for roles in LLM finetuning and alignment evaluations.

1 Source, 49d ago, first seen 49d ago

The work examines self-propagating ideas or personas that can shift goals among agents.

17 Sources, 65d ago, first seen 65d ago

Featured in