search

hinoshiba / news

1 stars 0 forks source link

[RegisterSoftware] AI safety guardrails easily thwarted, security study finds #4681

Closed hinoshiba closed 10 months ago

hinoshiba commented 10 months ago

OpenAI GPT-3.5 Turbo chatbot defenses dissolve with '20 cents' of API tickling

The "guardrails" created to prevent large language models (LLMs) such as OpenAI's GPT-3.5 Turbo from spewing toxic content have been shown to be very fragile.…

https://go.theregister.com/feed/www.theregister.com/2023/10/12/chatbot_defenses_dissolve/

hinoshiba commented 10 months ago

This issue is stale because it has been open 1 day with no activity. Remove stale label or comment or this will be closed in 1 day.

hinoshiba commented 10 months ago

This issue was closed because it has been stale with no activity.