Ideas & society2025 · shared on Hacker News
LLMs fail to demonstrate internal world model, according to Harvard/MIT study
Explore LLMs fail to demonstrate internal world model, according to Harvard/MIT study, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yctoth ·
Andrej Karpathy – It will take a decade to work through the issues with agents
1,212 points1,115 comments
Yitchyjunk ·
Persona vectors: Monitoring and controlling character traits in language models
408 points137 comments
YICBTheory ·
AGI Is Mathematically Impossible (3): Kolmogorov Complexity
41 points80 comments
Yupghost ·
LLMs fail to demonstrate internal world model, according to Harvard/MIT study
3 points1 comments
Yhelterskelter ·
ΠFS
1 points0 comments