Alex Tamkin

@alextamkin

machine learning, science & society @AnthropicAI | recently: Clio, Anthropic Economic Index, Claude Artifacts | prev: phd @StanfordAILab, @stanfordnlp

following
followers

In AI-agent trial, analysts reportedly matched agents’ assigned preferences on 86% of four analytical choices

Anthropic reports 77% repeated an agent’s argument in at least one post-task answer, while only 15% credited the agent.

15 Sources, 14h ago, updated 14h ago

Featured in

In AI-agent trial, analysts reportedly matched agents’ assigned preferences on 86% of four analytical choices

Featured in

In AI-agent trial, analysts reportedly matched agents’ assigned preferences on 86% of four analytical choices