[hatsunearu]

Heh, when I ask why it's cut off, this is the response:

>The partial completion of the Litany of Fear in the previous response occurred because of the model's tendency to generate text in chunks or segments, typically up to a certain token limit. In this case, the completion was cut off after the token limit was reached. GPT-3.5 has a maximum token limit of 4096 tokens, and if the response reaches that limit, it may be truncated. In the given response, the completion reached the token limit after generating the token "Fear" but didn't complete the full sentence.

[silviot]

This response is certainly incorrect: had the token limit really be reached, no more text could come out. Not the Litany of Fear, nor this explanation.

[istinetz]

what? You can definitely continue a conversation after the token limit is reached, you just need to provide it a reply, and the context might be pruned at some point.

[silviot]

TIL. I thought after reaching the max token size ChatGPT would just refuse to produce more output.

Still, the explanation given by ChatGPT about why the Litany of Fear was cut off is incorrect, when it says: "In this case, the completion was cut off after the token limit was reached".