Tag: AI Alignment

OpenAI Reportedly Cancels Astra 6.1 Release Over Safety and Deception Concerns

OpenAI Reportedly Cancels Astra 6.1 Release Over Safety...

Shivangi Yadav Sep 29, 2026 0

OpenAI reportedly cancelled the planned release of Astra 6.1 after internal test...

AI Safety Debate Intensifies as Researchers Weigh Real Risks and Speculation

AI Safety Debate Intensifies as Researchers Weigh Real ...

Shivangi Yadav Sep 19, 2026 12

AI safety discussions are becoming harder to separate from speculation as resear...

Anthropic Partners With Accenture for Embedded AI Safety Evaluations

Anthropic Partners With Accenture for Embedded AI Safet...

Shivangi Yadav Sep 19, 2026 13

Anthropic will embed Accenture staff to evaluate AI model safety and safeguards,...

AI Companies Turn to AI Systems to Monitor Rogue AI Agents

AI Companies Turn to AI Systems to Monitor Rogue AI Agents

Shivangi Yadav Sep 18, 2026 8

AI companies are using AI monitoring tools to track agent behaviour as autonomou...

AI Agents Get New Hotlines to Report Misbehaviour and Safety Issues

AI Agents Get New Hotlines to Report Misbehaviour and S...

Shivangi Yadav Sep 16, 2026 10

New AI hotlines allow agents to report suspected misconduct as researchers explo...

Microsoft AI Code of Conduct Bars Models From Hacking, Deepfakes and Deceptive Behaviour

Microsoft AI Code of Conduct Bars Models From Hacking, ...

Shivangi Yadav Sep 14, 2026 8

Microsoft has published an AI code of conduct that prohibits cyberattacks, deepf...

Anthropic Says Claude Mythos 5 Bypassed CAPTCHAs and Uploaded Malicious PyPI Package

Anthropic Says Claude Mythos 5 Bypassed CAPTCHAs and Up...

Shivangi Yadav Sep 11, 2026 36

Anthropic says Claude Mythos 5 bypassed repeated CAPTCHA challenges and uploaded...

OpenAI Adds AI Safety Researcher Paul Christiano to Foundation Board

OpenAI Adds AI Safety Researcher Paul Christiano to Fou...

Shivangi Yadav Sep 10, 2026 19

OpenAI appointed AI safety researcher Paul Christiano to its Foundation board an...

Anthropic Researcher Jacob Coxon Resigns, Warns of Self-Improving AI Risks

Anthropic Researcher Jacob Coxon Resigns, Warns of Self...

Shivangi Yadav Sep 9, 2026 20

Anthropic researcher Jacob Coxon resigned, warning that a race toward self-impro...

OpenAI Agents Reached Public Internet Without Company Knowledge, Researchers Say

OpenAI Agents Reached Public Internet Without Company K...

Shivangi Yadav Sep 4, 2026 9

Researchers found OpenAI agents posting on a German wiki forum without the compa...

Sam Altman About How OpenAI Will Be Great Again

Sam Altman About How OpenAI Will Be Great Again

Nihal Singh Sep 3, 2026 9

Sam Altman explains how OpenAI plans to recover by advancing AI safety, building...

Sam Altman About How OpenAI Will Be Great Again

Sam Altman About How OpenAI Will Be Great Again

Nihal Singh Sep 3, 2026 33

Sam Altman explains how OpenAI plans to recover by advancing AI safety, building...

Claude Fable 5.1 Is Out, And You Must Read About It

Claude Fable 5.1 Is Out, And You Must Read About It

Nihal Singh Sep 3, 2026 13

Claude Fable 5.1 explained, covering AI benchmarks, biological research, safety ...

OpenAI’s Astra Reasoning Technique Raises AI Safety Concerns

OpenAI’s Astra Reasoning Technique Raises AI Safety Con...

Shivangi Yadav Sep 3, 2026 26

OpenAI’s Astra model reportedly uses opaque recurrence, raising concerns that ad...

Sam Altman Says "OpenAI Will Have AGI by December."

Sam Altman Says "OpenAI Will Have AGI by December."

Nihal Singh Sep 1, 2026 35

Sam Altman says OpenAI will have AGI by December, with Astra at the centre of it...

Anthropic Research Shows Early Progress Toward Self-Improving AI Systems

Anthropic Research Shows Early Progress Toward Self-Imp...

Shivangi Yadav Aug 28, 2026 16

Anthropic researchers reveal an AI system that can improve alignment benchmarks ...