🧩 Philosophy 11h ago · 1a3orn

The Unintelligibility is Ours: Notes on Chain-of-Thought

Less Wrong
View Channel →
Source ↗ 👁 0 💬 0
Many people seem to think that the chains-of-thought in RL-trained LLMs are under a great deal of "pressure" to cease being English. The idea is that, as LLMs solve harder and harder problems, they will eventually slide into inventing a "new language" that lets them solve problems better, more efficiently, and in fewer tokens, than thinking in a human-intelligible chain-of-thought.
I'm less sure this will happen, or that it will happen before some kind of ASI. As a high-level intuition pump for

Comments (0)

Sign in to join the discussion

More Like This

📰
Philosophy of Microbiology
Stanford Encyclopedia of Philosophy · 4h ago
Claude Mythos #2: Cybersecurity and Project Glasswing
LessWrong · 11h ago
📰
Anthropic is Really Pushing the Frontier, What do I Think About This?
LessWrong · 11h ago
Slaughterhouse 666: Kicking and A-gouging in the Pus and the Gore and the Fear
3:AM Magazine · 13h ago
📰
"Close Enough" as a Primitive in Intelligent Systems
LessWrong · 14h ago
📰
Foundational Beliefs
LessWrong · 14h ago