pith. machine review for the scientific record. sign in

The hacking of ChatGPT is just getting started

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2023 1

verdicts

UNVERDICTED 1

representative citing papers

Jailbroken: How Does LLM Safety Training Fail?

cs.LG · 2023-07-05 · unverdicted · novelty 6.0

LLM safety training fails due to competing objectives and mismatched generalization, enabling new jailbreaks that succeed on all unsafe prompts from red-teaming sets in GPT-4 and Claude.

citing papers explorer

Showing 1 of 1 citing paper.

  • Jailbroken: How Does LLM Safety Training Fail? cs.LG · 2023-07-05 · unverdicted · none · ref 13

    LLM safety training fails due to competing objectives and mismatched generalization, enabling new jailbreaks that succeed on all unsafe prompts from red-teaming sets in GPT-4 and Claude.