LLM Attacks

Caute_cautim — Mon, 09 Oct 2023 10:40:29 GMT

Hi All

“The researchers found that they could break through the guardrails of open source systems by appending a long suffix of characters onto each English-language prompt fed into the system… There is no obvious solution”

https://arxiv.org/abs/2307.15043

A very interesting piece of research indeed - great reading.

Prepare for the onslaught....

Plus update from the New York times: https://www.nytimes.com/2023/07/27/business/ai-chatgpt-safety-research.html

Regards

Caute_Cautim

topic LLM Attacks in Threats

LLM Attacks