On: GPT-5.6 Sol Ultra will be in Codex

[brookst]

Yes. Tell me why it’s different without using circular reasoning?

[rowanG077 → brookst]

They're different mechanisms.

Teaching modifies the learner. Prompting doesn't modify the model. It provides additional context that influences a single inference. A person who has learned something can apply it years later without being reminded. An LLM generally cannot unless the knowledge is incorporated into the model itself or provided again.

[unparagoned → rowanG077]

A human requires sleep the update their mental model to use that learning years later.

Take a human and prevent them from sleeping after covering a fact then years later they won’t know it.

[rowanG077 → unparagoned]

sleeping helps learning, but people can learn without sleep. You can teach something to a person and they can usually do it immediately in some capacity. If you prevent a person from sleeping they will have reduced capacity to remember things. But it will most certainly not be zero.

[SR2Z → rowanG077]

Right, but "provided again" is what SKILL.md or whatever else are for.

The value of LLMs is that they're stateless. With sufficiently detailed documentation and a well-bounded task, they are quite useful.

[rowanG077 → SR2Z]

I don't think it's generally thought of an advantage that LLMs are stateless. In deployment it's nice, it would be much better if the model could continually learn.

I'm not claiming LLMs are not useful, they most certainly are.