[tech_ken]

LLMs don't have an internal representation of "facts", they generate text based entirely on the conversation history. If it's properly tuned it will remain consistent with facts it's stated earlier in the conversation, but this is just a feature of the training data demonstrating this type of consistency, the model itself doesn't understand that something being "true" means it's true for all time. In practice the conversation sequence strongly determines the model's internal state, so you need to preserve the entire conversation history if you're trying to demonstrate some particular model outcome.

[david-gpu]

> LLMs don't have an internal representation of "facts", they generate text based entirely on the conversation history.

If output only depended on the conversation history, you would get the exact same output if you started ten conversations in the exact same way, and that doesn't happen.

LLMs encode their knowledge in their parameters, which are fixed after training is complete and thus well before the conversation begins. The context of the conversation does also affect the output you get from the LLM, because by design they take context into account, but it is entirely untrue that the output is "they generate text based entirely the conversation history".

[tech_ken]

Sure I guess I meant "entirely on the conversation history" in the sense that a prompt is a sin qua non of an outcome, and the outcome is dependent on the specific prompt(s). I was using the word informally as an emphasizer of "conversation history", did not intend to imply that it didn't have parameters or other internal things which effected the output, just the output at any given point in time is path-dependent on the prompts you put.

[mvdtnz]

Half the people on this forum are convinced that LLMs are actually intelligent and have an actual internal world model in their "brains". I wonder how they square this with the fact that it will give wildly different answers to the same question with subtle changes in context.

[floren]

Oh, easy: they'll say the LLMs have learned to "code switch"