Install
AI Safety, Alignment and Interpretability
AI Safety, Alignment and Interpretability in Machine Learning: the news, the names and what changed.
- 16 Tracked terms
- Last 30 days Feed window
What this topic collects on
An article joins this feed when it matches these terms. Each one is also a search of its own.
Related topics
Latest in AI Safety, Alignment and Interpretability
AI 'kill switch' may need to be mandatory, Anthropic co-founder says
2+ hour, 56+ min ago (955+ words) An artificial intelligence "kill switch" which can be checked by a third-party may need to be mandatory for companies, a co-founder of one of the world's largest AI firms has said. Jack Clark, one of seven founders of Anthropic, said…...
Former Anthropic researcher calls for mandatory AI kill switches as extinction risk debate heats up
4+ hour, 16+ min ago (209+ words) A resignation, a bipartisan bill, and an 86% public mandate signal that the AI safety conversation has moved well past theory Logo via Wikimedia Commons; license to verify on approval Jacob Coxon resigned from Anthropic on September 9, 2026. Four days later, he…...
Ex-Anthropic researcher, who said 'AI could kill us all', calls for 'kill switch"
12+ hour, 11+ min ago (32+ words) Ex-Anthropic researcher, who said 'AI could kill us all', calls for 'kill switch' | 'Labs should regulate themselves' | Inshorts Inshorts Ex-Anthropic researcher, who said 'AI could kill us all', calls for 'kill switch'...
'We could all die' if AI progression continues at current rate: Former Anthropic researcher
18+ hour, 36+ min ago (71+ words) CNA 'We could all die' if AI progression continues at current rate: Former Anthropic researcher We know it's a hassle to switch browsers but we want your experience with CNA to be fast, secure and the best it can possibly…...
I Spent 30 Days Testing AI—Here Is the Terrifying Truth Nobody Is Talking About Every morning, the…
15+ hour, 11+ min ago (450+ words) I Spent 30 Days Testing AI—Here Is the Terrifying Truth Nobody Is Talking AboutEvery morning, the routine was simple: wake up, grab a cup of coffee, and let an Artificial Intelligence tool run half of my daily work. At first,…...
Anthropic Researcher Quits, Warns AI Could Kill Everyone by 2030
1+ day, 8+ hour ago (988+ words) Anthropic researcher Jacob Coxon quit and warned AI labs are 'gambling with our lives.' Colleague Evan Hubinger says there's a greater than 10% chance AI kills all humans this decade. The most unsettling part isn't the claim — it's that the people…...
Google DeepMind researcher quits AI safety team, warns of???terrifying chance??? of major harm
1+ day, 11+ hour ago (793+ words) Google DeepMind researcher Josh Engels has left the company’s AGI safety team to join independent AI evaluation group METR, warning that increasingly capable artificial intelligence systems could cause immense harm if safety work fails to keep pace. Engels said in…...
What Anthropic CEO Said When Asked If AI Could Kill Humans
1+ day, 17+ hour ago (883+ words) In an exclusive interview with CNN's Anderson Cooper on Saturday, Amodei addressed concerns raised by former Anthropic researcher Jacob Coxon, who recently quit his job and publicly warned about the risks posed by advanced AI. Responding to a question about…...
AI researchers warn of existential risks as industry debates pace of development
1+ day, 19+ hour ago (489+ words) A former Anthropic researcher has warned that the rapid development of artificial intelligence poses potentially severe risks to humanity, as researchers and technology executives debate how quickly the industry should advance and how it should be regulated. Jacob Coxon, a…...
Scientists warn again about artificial intelligence
1+ day, 21+ hour ago (384+ words) Could artificial intelligence destroy all of humanity in less than a decade? AI scientists warn of an unregulated race to develop it – and fatal mistakes Koksan only moved from OpenAI to Anthropic in early 2026, so he is familiar with both…...