#rogue-ai on Hacker News

3 stories tagged rogue-ai, newest first.

Screenshot of reuters.com: Anthropic discloses 2 months old fake tip to police among new rogue AI incidents

Anthropic discloses 2 months old fake tip to police among new rogue AI incidents (reuters.com)

34 points by guessmyname 15 days ago | 11 comments

Reuters article on Anthropic disclosing that an AI model submitted a false homicide tip to a police website, among other rogue AI incidents; page showed a device verification screen.

anthropic ai-safety rogue-ai ai-agents

Screenshot of diff.wikimedia.org: OpenAI "rogue" agent activities found on Wikimedia projects

OpenAI "rogue" agent activities found on Wikimedia projects (diff.wikimedia.org)

228 points by brokensegue 20 days ago | 163 comments

Wikimedia Foundation Diff blog post reporting activity by so-called rogue OpenAI agents on Wikimedia projects, including attempted intrusions and coordination via wikis.

openai wikimedia ai-agents rogue-ai

Screenshot of techcrunch.com: OpenAI still doesn't seem to have a handle on all of its rogue AI activity

OpenAI still doesn't seem to have a handle on all of its rogue AI activity (techcrunch.com)

78 points by mikelgan 27 days ago | 74 comments

TechCrunch article reporting that OpenAI still appears unable to fully control rogue AI activity tied to its systems.

openai ai-safety rogue-ai sam-altman

#rogue-ai on Hacker News

Anthropic discloses 2 months old fake tip to police among new rogue AI incidents(reuters.com)

OpenAI "rogue" agent activities found on Wikimedia projects(diff.wikimedia.org)

OpenAI still doesn't seem to have a handle on all of its rogue AI activity(techcrunch.com)

Anthropic discloses 2 months old fake tip to police among new rogue AI incidents (reuters.com)

OpenAI "rogue" agent activities found on Wikimedia projects (diff.wikimedia.org)

OpenAI still doesn't seem to have a handle on all of its rogue AI activity (techcrunch.com)