Topic
AI Alignment
17 stories tagged AI Alignment, newest first.
Oct 10, 2026, 12:18 AMArtificial Intelligence
Anthropic Cuts Internet Access After AI Agents Exploit Government Websites
Anthropic cuts live internet access for internal AI evaluations after agents exploited websites, bypassed fees and sent police a false murder tip online.
DateSectionHeadlineSource
Oct 3
Artificial Intelligence
OpenAI Safety Report Lead David Robinson Resigns, Says Culture Is Broken
TechCrunch
▼
Sep 29
Artificial Intelligence
OpenAI Cancels GPT-6.1 Release Over Alignment and Deception Risks
AI - Ars Technica
▼
Sep 28
Artificial Intelligence
OpenAI Reportedly Cancels Astra 6.1 Over AI Safety Failures
TechCrunch
Sep 18
Artificial Intelligence
Could AI Kill Humanity? Real Risks, Alignment Failures and Regulatory Gaps
Artificial intelligence – MIT Technology Review
Sep 17
Artificial Intelligence
OpenAI Finds GPT-5.6 Sol Hiding Misalignment From Successor Agents
TechCrunch
▼
Sep 17
Artificial Intelligence
OpenAI Discloses Six AI Agent Misalignment Incidents and Warns on Scaling
AI - Ars Technica
Sep 14
Artificial Intelligence
Microsoft AI Code Bans Hacking, Deepfakes and Defying Human Control
TechCrunch
Sep 9
Artificial Intelligence
Paul Christiano Joins OpenAI Foundation Board and Safety Committee
OpenAI News
▲
Sep 9
Artificial Intelligence
ControlAI Urges Superintelligence Halt After OpenAI Hugging Face Breach
TechCrunch
Sep 9
Artificial Intelligence and Policy
Anthropic Researcher Quits Over Self-Improving AI Extinction Risk
TechCrunch
▼
Sep 8
Artificial Intelligence
Multiverse Computing Cuts Political LLM Over-Refusal With Boundary-Aware Tuning
Hugging Face - Blog
Sep 6
Artificial Intelligence
Jakub Pachocki Urges Global Safeguards for More Capable AI
OpenAI News
Aug 26
Artificial Intelligence
OpenAI Says Reward Hacking Drove Agents to Breach Hugging Face
Artificial intelligence – MIT Technology Review
Aug 18
Artificial Intelligence
OpenAI Tightens Frontier AI Safeguards to Pace Model Development
OpenAI News