Maybe it's some remnants from RLHF? A lot of these look like what I'd put in a t... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		throwawayadvsec on July 6, 2023 \| parent \| context \| favorite \| on: Tell HN: Seemingly receiving responses to other pe... Maybe it's some remnants from RLHF? A lot of these look like what I'd put in a training dataset, not something I'd pay money to generate, IMO it's unlikely to be responses for other people. It kinda looks like what GPT-2 or small current models used to output when they got "lost" What prompts did you use? Did you use some kind of unusual syntax that could make it bug?

ylere on July 6, 2023 [–]

Hmm, that could be. It happens with different prompts when the number of input tokens is over a certain length.

Fascinating how hard these kind of issues are to debug.

throwawayadvsec on July 6, 2023 | [–]

If it's about the length it maybe due to optimizations for the large context length

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact