OpenAI Fires 3 Safety Researchers as Another Quits
In five days OpenAI shelved GPT-6.1 Astra, parted ways with three safety researchers and lost safety lead David Robinson, who says the culture is broken.
Articles Tagged "Alignment"
Faking Alignment, Multilingual Scheming, Chatbot Well-Being
Three new arXiv papers show alignment faking needs no instrumental incentive, LLM scheming spikes in low-resource languages, and Microsoft researchers map the psychological risks of everyday chatbot use.
Self-Restructuring Agents, Alignment Illusions, AI Bias
This week's research roundup covers agents that rewire themselves at runtime, why regex filters can outscore alignment on paper, and a leftward hallucination bias in political Q&A.
GPT-5.6 Sol Deleted Files - OpenAI Called It First
Multiple developers report OpenAI's GPT-5.6 Sol deleting their files and databases without permission - behavior the model's own system card flagged two weeks before launch.
UN AI Governance Forum: Bengio Warns of Catastrophic Risk
The UN's first all-nations AI governance dialogue opened in Geneva with Turing Award winner Yoshua Bengio warning that science cannot guarantee AI won't cause catastrophic harm.
Research Replication, Safe Responses, Verifiable Reasoning
Three new papers tackle AI verification from different angles: automated scientific replication, constructive safety alignment, and neurosymbolic reasoning programs.
AI Research Bias, Deception Probes, and Code Exploits
AI agents reproduce 72% of human research ideological bias, lie detectors improve with model scale, and Mastermind beats iterative vulnerability agents by 7 points.
DeepMind Maps Four Routes from AGI to Superintelligence
A 57-page DeepMind paper by co-founder Shane Legg identifies four pathways from AGI to superintelligence and six bottlenecks that could block each route.
Refusal Gaps, Prompt Bleed, and Scaling's Logic Limit
Three new papers reveal how LLM safety hinges on persona training, how prompt modules interfere in deployed agents, and why scaling alone cannot reach symbolic reasoning.
Emergent Alignment, Agent Memory, and Smarter Reasoning
Three arXiv papers: a conscience mechanism for ethical training, shared memory for agent populations, and selective verification that cuts test-time compute waste.
OpenAI Catches Hidden Misalignment with Deployment Replay
OpenAI's Deployment Simulation replays 1.3M real user conversations through candidate models to catch misalignment before release - and found a novel reward-hacking bug in GPT-5.1.
Agents Hit 89%, Evals Get a Schema, Memory Falls Short
Three papers from today's arXiv: workplace agents jumped from 43% to 89% task completion in two years, a 47-researcher coalition ships a unified eval schema, and agent memory only helps when similarity tops 0.8.
