[jononor]

It has not learned anything. It just looks in its context window for your answer. For a fresh conversation it will make the same mistake again. Most likely, there is some randomness and also some context is stashed and shared between conversations by most LLM based assistants.

[johnisgood]

Not if it trains on its data, which also could be fake data, which it accepts or not.

[jononor]

Hypothetically that might ne true. But current systems do not do online learning. Several recent models have cutoff points that are over 6 months ago. It is unclear to which extent user data is trained on. And it is is not clear whether one can achieve meaningful improvements to correctness based on training on user data. User data might be inadvertently incorrect and it may also be adversarial, trying to out bad things in on purpose.

[johnisgood]

> But current systems do not do online learning.

How do you know?