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 1 year 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 1 year ago
minorninth@lemmy.world 1 year 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 1 year 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.