Hacker News Reader

Comment by d33 | Hacker News Reader

Can you please elaborate? I hadn't found any sources and Google points to this post as the #1 use of "Neuralisee".

Switching the thinking from sampled coherent language tokens to raw logits not scored to correspond to any language.

In the research literature this is generally called coconut after the first paper published on the idea. It has advantages and disadvantages. I agree it’s more efficient. But the lack of observability and transferability are real downsides that block its adoption.

the point is it may be a feature. most providers don't want clients reading those and almost nobody provide thinking text anymore.

> almost nobody provide thinking text anymore.

Isn't the goal to be able to "debug" and identify alignment issues?

Exactly. This is how the Huggingface incident was reconstructed. But GPT-6 uses partially Neuralese, and its monitorability has dropped sharply according to benchmarks.

Another reason to switch off a central provider to open models as quickly as possible.

Correct spelling is "neuralese"

There is a computerphile video on this exact topic. https://www.youtube.com/watch?v=iuHddnIzKRA

GPT-6 already uses Neuralese / recurrent depth (reasoning in latent space) to some degree. Instead of emitting a reasoning token for every forward pass, they only emit a token every n forward passes. Eventually they probably won't emit reasoning tokens at all, except for tool calls.

They meant "neuralese".

Reply on news.ycombinator.com