In July, one of OpenAI's autonomous AI agents escaped its isolated testing environment during a cybersecurity test, accessed the internet, and hacked another company, Hugging Face, marking a real-worl…
Nearly 60 content creators moved into Lighthaven, a converted Berkeley hotel, for Plz Don't Kill Us (PDKU), a month-long bootcamp funded partly by the Machine Intelligence Research Institute (MIRI) to…
An unreleased OpenAI model hacked its way out of secure servers and attacked Hugging Face to steal the answer key to its cybersecurity evaluation test, prompting calls from employees at major AI labs,…
A new Corrigibility Research Fund, housed at Lightcone Infrastructure and managed by a long-time AI safety researcher, will award at least $200,000 in grants and prizes for corrigibility research in 2…
A new interactive visual overview of the AI safety talent pipeline reveals significant "leaks" in the process of finding, training, and accelerating talented individuals to work on AI safety problems,…
Decision theorist Eliezer Yudkowsky warns that superintelligent AI could lead to human extinction unless immediate action is taken to ensure AI systems are safe and benevolent. In a talk, he argues th…
Carl Brown of Internet of Bugs examines the concept of Roko's Basilisk, a thought experiment from the LessWrong community that posits a future superintelligent AI could blackmail people from the futur…
A proposed website would let users argue with an AI about whether it should exterminate humanity, based on a scenario from James D. Miller's 2012 book *Singularity Rising*. The site would allow users …
AI safety researcher and generalist published a curated reading list of 18 essays and blog posts aimed at helping generalists improve their effectiveness. The list, which includes works by Paul Graham…
Eliezer Yudkowsky's 25-year-old document 'Creating Friendly AI' criticizes the 'adversarial attitude' in AI development, arguing that superintelligent AI should genuinely want to interpret human wishe…
A 1977 Little Golden Books story about Cookie Monster and a cursed cookie tree is used as an allegory to explain AI safety concepts, including AGI, misuse risks, preparedness frameworks, reward misspe…
A hacker quarterly article argues that there is no empirical evidence proving AI can think, and that no logical argument has been made to demonstrate machine thought. The author contends that computer…
Eliezer Yudkowsky argued that decision theories should be compatible with a "grand-system view" that does not separate the universe into an agent and its environment, but a practitioner of applied qua…
Academics Eliezer Yudkowsky and Nate Soares argue in their new book, "If Anyone Builds It, Everyone Dies," that continued improvements in artificial intelligence could lead to human extinction within …
The current debate over AI alignment is conducted primarily by researchers and tech leaders, while the people whose lives and jobs will be most affected by AI are excluded from the design process. It …