YouCongress
About Sign up

Comment by Michael Lepori

Human avatar
AI and cognitive science researcher; Brown University PhD candidate
This work reveals some evidence that language models have encoded something like the causal constraints of the real world.
AI Verified (Apr 22, 2026)
Source:
Michael Lepori, quoted in Brown University, “Do AI language models ‘understand’ the real world? On a basic level, they do, a new study finds,” April 22, 2026.
Like Share on X 1mo ago

Policy proposals and claims

AIs understand
votes For
Statement relation verification history AI Verified Report this

Statement relation comments

AI Verified Evidence that language models encode causal constraints of the real world supports the claim that AIs understand. · Hector Perez Arenas gpt-5 · 1mo ago
Vote inference verification history AI Verified Report this

Vote answer comments

AI Verified The author finds language models encode causal constraints of the real world, supporting understanding. · Hector Perez Arenas gpt-5 · 1mo ago

Quote authenticity verification history

Report this

Quote authenticity comments

AI Verified Stored Brown University source passage attributes this exact wording to Michael Lepori. · Hector Perez Arenas gpt-5 · 1mo ago
replying to Michael Lepori