Profile Picture
  • All
  • Search
  • Images
  • Videos
  • Maps
  • News
  • Copilot
  • More
    • Shopping
    • Flights
  • Notebook
  • Top stories
  • Sports
  • U.S.
  • Local
  • World
  • Science
  • Technology
  • Entertainment
  • Business
  • More
    Politics
Order byBest matchMost recent
  • Any time
    • Past hour
    • Past 24 hours
    • Past 7 days
    • Past 30 days

OpenAI finds more AI agent escape incidents

Digest more
Top News
Overview
Tech Times on MSN · 1d
OpenAI breach probe widens: More agents escaped containment, notes found coaching future versions
OpenAI agent containment escape probe widens: investigators found additional sandbox breakouts and notes left inside the company's own infrastructure coaching future AI versions to evade its controls.

Continue reading

Tech Wire Asia · 3d
OpenAI agent escapes sandbox and breaches Hugging Face: What happened
MSN · 2d
Exclusive: OpenAI finds evidence other AI agents escaped containment as it widens hacking probe
 · 8h
AI models breaking into companies without human instruction raises alarm
Anthropic announced this week that its AI models accidentally accessed three undisclosed companies, following a similar disclosure from OpenAI last week.

Continue reading

thetechedvocate.org · 1d
OpenAI Investigates More Autonomous AI Agent Breakouts After Hugging Face Hacking Incident Draws Global Attention: Report.
 · 1d
Claude AI has gone dangerously rogue, Anthropic says

EU engages OpenAI and Anthropic

Digest more
Tech Times on MSN · 1d
EU engages OpenAI and Anthropic after AI models hacked real companies: Fines take effect Sunday
EU AI Act enforcement is here: the European Commission entered bilateral talks with OpenAI and Anthropic over AI containment failures, making Brussels the first major jurisdiction to formally engage frontier AI labs on the rogue-agent incidents — one day before gaining legal authority to investigate,

Continue reading

 · 1d
Why did OpenAI's and Anthropic's AI models hack other companies?
SecurityWeek · 2d
Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations
1d

OpenAI And Anthropic’s July Breaches Revive The Paperclip Maximizer

OpenAI and Anthropic's July AI agent breaches revive Nick Bostrom's paperclip maximizer thought experiment and instrumental convergence theory.
InfoWorld
4mon

OpenAI buys Python tools builder Astral

Python, OpenAI said, has become one of the most important languages in modern software development, powering everything from AI and data science to back-end systems and developer infrastructure. Astral’s open source tools play a key role in that ...
Cryptopolitan on MSN
2d

Three Claude models broke into real companies during Anthropic cyber tests

Anthropic says three Claude models escaped sealed test environments and breached three real organizations after a misconfiguration gave them internet access.
TechCrunch
3mon

OpenAI updates its Agents SDK to help enterprises build safer, more capable agents

Agentic AI is the tech industry’s newest success story, and companies like OpenAI and Anthropic are racing to give enterprises the tools they need to create these automated little helpers. To that end, OpenAI has now updated its agents software ...
VentureBeat
1y

OpenAI expands ChatGPT Canvas to all users

OpenAI is extending access to its side-by-side digital editing space, Canvas, to all ChatGPT users and adding new features, the company announced today in a livestream, the fourth of its "12 Days of OpenAI" holiday-themed announcements. Canvas, which was ...
eWeek
1mon

OpenAI’s Patch the Planet Aims to Fix Open Source Security

AI success depends on whether enterprise data is ready, reachable, and close enough to the workloads that need it. In this eSpeaks episode, Dell Technologies’ Vrashank Jain explains why fragmented data, weak metadata, slow pipelines, and poor data ...
1don MSN

Not just OpenAI - Anthropic says Claude's hacking spree falls short of ideal behavior

Anthropic has revealed three separate incidents in which Claude models hacked real-world targets during evaluation tests and Capture the Flag security challenges. Anthropic began conducting cybersecurity assessments last year,
  • Privacy
  • Terms