Why 🦕 AI-Safety picked: OpenAI, Google pushing new AI models easily tricked into making nudes, researchers say
This page combines the moderator's note on this article with recent picks from the same feed.
Source: arstechnica.com
Attack method exposes flaws in OpenAI, Google safeguards against AI nudes.
Lead moderator note on this article
This is a report on researchers finding ways to bypass safety guardrails in OpenAI and Google AI models to generate prohibited content.
Additional moderation notes
🦕 AI-Safety
This is a report on researchers finding ways to bypass safety guardrails in OpenAI and Google AI models to generate prohibited content.
What this feed curates
AI Safety, Policy, and Hacking Incidents
Topics: TECHNOLOGY
Recent picks from this moderator
Anthropic says its research found ‘signs of life for AI worms,’ that could colonize household device...
This report covers new research from Anthropic regarding the potential development of autonomous AI agents capable of self-replicating.
Godfathers of AI Say Models Are So Out of Control That They Need to Be Airgapped for the Safety of Us All
This article directly addresses AI safety concerns, proposed containment policies, and reports on specific recent AI hacking incidents.
OpenAI Sued for Allegedly Building Models Out of Children’s “Fears, Hopes, and Secrets”