Tag: Alignment

Natural language processing

4 Min Read

Safety assessments show that OpenAI’s o3 is probably the company’s riskiest AI model to date

By Editorial Team

April 18, 2025

Read Article

Natural language processing

3 Min Read

OpenAI updates risk framework to assess advanced AI capabilities

By Editorial Team

April 16, 2025

Read Article

Natural language processing

2 Min Read

Security testing under pressure as OpenAI accelerates AI development

By Editorial Team

April 11, 2025

Read Article

Natural language processing

4 Min Read

Training AI on bad code makes it admire Hitler and want to harm humans, study finds

By Editorial Team

March 1, 2025

Read Article

Natural language processing

7 Min Read

Altman’s naive dream of AI equality

By Editorial Team

February 19, 2025

Read Article

Natural language processing

4 Min Read

creeping AI development could lead to our ‘gradual disempowerment’

By Editorial Team

February 6, 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

3 Min Read

OpenAI’s o1-preview model manipulates game files to force a win against Stockfish in chess

By Editorial Team

December 30, 2024

Read Article

Natural language processing

4 Min Read

Ex-OpenAI employee warns US Senate

By Editorial Team

September 19, 2024

Read Article

Natural language processing

2 Min Read

New oversight committee gains power to delay OpenAI releases over safety concerns

By Editorial Team

September 17, 2024

Read Article