Or I should explain better: most training samples will be cut off at the top, so the network sort of learns to ignore it a bit.
Comment on Little Bobby Tables has a baby sister. Meet Sally Ignore Previous Instructions.
vcmj@programming.dev 11 months agoYes, that’s by design, the networks work on transcripts per input, it does genuinely get cut off eventually, usually it purges an entire older line when the tokens exceed a limit.
vcmj@programming.dev 11 months ago
minorninth@lemmy.world 10 months ago
I’m talking about using the ChatGPT API to make a chat bot. Even when the user’s input is just one sentence, it can cause ChatGPT to forget its prompt.
vcmj@programming.dev 10 months ago
Ah, even then it could just be a consequence of training samples usually being chronological so it learns to think that way. I did find the pattern also applies to GPT trained on long articles where you’d expect it not to, so wanted to just explain why that might be.