Hacker Newsnew | past | comments | ask | show | jobs | submit | cryptohell's submissionslogin
1.
Can we bootstrap AI Safety despite being unable to even define it? (arxiv.org)
2 points by cryptohell 20 days ago | past | 2 comments
2.
Optimality of Frequency Moment Estimation (weizmann.ac.il)
8 points by cryptohell 11 months ago | past | 1 comment
3.
LLMs can hide arbitrary undetectable information in their responses (twitter.com/zamirphd)
3 points by cryptohell on Jan 22, 2024 | past | 3 comments
4.
LLMs can hide arbitrary information in their responses, undetectably (arxiv.org)
1 point by cryptohell on Jan 22, 2024 | past
5.
Undetectable Watermarks for LLMs (arxiv.org)
3 points by cryptohell on June 30, 2023 | past
6.
Undetectable Watermarks for LLMs (arxiv.org)
2 points by cryptohell on June 17, 2023 | past
7.
Undetectable Watermarks for Language Models (arxiv.org)
1 point by cryptohell on June 16, 2023 | past | 1 comment
8.
Undetectable Watermarks for Language Models (iacr.org)
135 points by cryptohell on June 2, 2023 | past | 69 comments
9.
(Provably) Undetectable Watermarks for LLMs (iacr.org)
1 point by cryptohell on May 30, 2023 | past

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

Search: