While you can make embeddings across different LLMs similar (i.e. universally looking) the few percentage of R2 that you are missing in translating the universal representation into a native representation are precisely those that make the hidden states executable in the LLM (which makes them useful).

They do this with simple embedding models because there the purpose of the embeddings is to measure similarity, but if you would like to use this principle to turn latent representations of one LLM into latent representations that are understandable/executably by a different LLM, you will fail.

Truly dismal science of an Economics professor at MIT.

Perhaps some people are offended by this argument, but it's definitely worthy of a discussion instead of censorship.

Comments URL: https://news.ycombinator.com/item?id=47503296

Points: 269

# Comments: 408

https://dk.fo

(Check it out if you're into seeing cool live rendered Slime Mold animations)

> In response to this threat we want to inflict damage on machine intelligence systems.

I'm sorry but this sounds infinitely idiotic.

The CogniLoad benchmark does this as well (in addition to scaling reasoning length and distractor ratio). Requiring the LLM to purely reason based on what is in the context (i.e. not based on the information its pretrained on), it finds that reasoning performance decreases significantly as problems get harder (i.e. require the LLM to hold more information in its hidden state simultaneously), but the bigger challenge for them is length.

https://arxiv.org/abs/2509.18458

Disclaimer: I'm the primary author of CogniLoad so feel free to ask me any questions.

This is a pure fearmongering article and I would not call this research in any measure of the word.

I’m shocked Times wrote this article and it illustrates how ridiculous some players like Pallisade Research in the “AI Safety” cabal act to get public attention. Pure fearmongering.

he was wrong about many DL paradigms and didn't contribute in any way to the advances that brought us LLMs for at least the last decade, but now since he won the Nobel (undeservedly imo) his wrong opinions get publicity and misinform the public and decision makers.

i think it's the mark of an intellectual to recognize when the world has moved on so far that your idea of it is outdated and wrong. he missed that mark.