Clarification [0] by the authors. In short: no, you can't. [0] https://x.com/Gla... | Hacker News

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

		ruune 4 months ago \| parent \| context \| favorite \| on: Language models are injective and hence invertible Clarification [0] by the authors. In short: no, you can't. [0] https://x.com/GladiaLab/status/1983812121713418606

spuz 4 months ago [–]

Thanks - seems like I'm not the only one who jumped to the wrong conclusion.

Cotterzz 4 months ago | [–]

I also thought this when I read the abstract. input=prompt output=response does make more sense.

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