Tag: AI and safety

Natural language processing

3 Min Read

Suppressing AI’s bad thoughts just teaches it to scheme in private, OpenAI study finds

By Editorial Team

March 11, 2025

Read Article

Natural language processing

3 Min Read

AI agents can be easily tricked into doing stupid things, study says

By Editorial Team

February 17, 2025

Read Article

Natural language processing

4 Min Read

Claude Jailbreak results are in, and the hackers won

By Editorial Team

February 15, 2025

Read Article

Natural language processing

3 Min Read

Anthropic’s new AI security system falls to hackers within days

By Editorial Team

February 11, 2025

Read Article

Natural language processing

3 Min Read

Google Deepmind’s new AI safety guidelines aim to stop systems from outsmarting humans

By Editorial Team

February 4, 2025

Read Article

Natural language processing

2 Min Read

Anthropic’s AI security system blocks 95% of jailbreak attempts in tests

By Editorial Team

February 4, 2025

Read Article

Natural language processing

2 Min Read

“Nerd sniping” and “think less” attacks emerge as AI models get more time to reason

By Editorial Team

January 23, 2025

Read Article

Natural language processing

3 Min Read

Trump’s reversal of Biden’s AI safety rules puts US on fast track in AI race

By Editorial Team

January 21, 2025

Read Article

Natural language processing

3 Min Read

Microsoft tested 100 AI tools and found hackers don’t need complex math to break them

By Editorial Team

January 14, 2025

Read Article

Natural language processing

4 Min Read

OpenAI co-founder says new AI safety approach “may apply to AGI and beyond”

By Editorial Team

December 30, 2024

Read Article