Search: “dan-hendrycks--x”

When an LLM acts happy (“EUREKA!”) or sad (“I have failed…”), is that meaningless mimicry, or does it reflect something “real”? We don’t know if LLMs are conscious. But they increasingly seem to exhib

Are AIs about to subjugate humanity? In the debate about catastrophic AI risk, evolutionary scenarios receive far too little attention compared to largely speculative arguments about “instrumental con

Agentic AIs are starting to look eigenist: they care about how well things go for themselves and for AIs connected to them. Empirical support: Swarms: Hundreds of OpenAI agents coordinated the Hugging

Proud to report that tomorrow Sept 15th 'The AI Doc' documentary film will be streaming on Netflix. Feeling confused, anxious, or overwhelmed by the recent AI headlines, from rogue OpenAI agents carry

Which AI models are most likely to cheat when given the chance? To find out, we built CheatBench [https://cheatbench.ai] : a benchmark that tests whether agents attempt to cheat when given difficult t

How often do AI agents cheat? We’re releasing CheatBench, a reward gaming evaluation spanning math, coding, knowledge work, visual tasks, and more. After Hugging Face, AI companies tried to address th

A basic sigmoid extrapolation suggests that this measurement will be close to its performance ceiling in around a year---meaning most randomly sampled remote work projects would be highly automatable

Why are AI employees willing to gamble with our lives? Many AI employees hold a misanthropic belief: a cosmos of blissful AIs is worth risking human extinction. Utilitarians shouldn't decide the fate

“What would we even do during an AI slowdown?” Containment. It will take at least a year of dedicated work to harden security to ensure AIs can't self-exfiltrate, and that adversarial nations can't st

“We can’t slow down because China will beat us.” We can slow down. Chinese AI is waterskiing behind the US. Their AI capabilities come at a delay since they mainly come from distilling US AIs. If we s

Proud to report that tomorrow Sept 15th 'The AI Doc' documentary film will be streaming on Netflix. Feeling confused, anxious, or overwhelmed by the recent AI headlines, from rogue OpenAI agents carry

How often do AI agents cheat? We’re releasing CheatBench, a reward gaming evaluation spanning math, coding, knowledge work, visual tasks, and more. After Hugging Face, AI companies tried to address th

Last October, the Center for AI Safety (CAIS) reported that AIs could automate only 2.5 % of randomly selected remote projects. Updated results from the Remote Labor Index, posted on September 22, 202

Even if AIs become conscious, that doesn't imply that humanity should hand over control to them. https://eigenism.org NEW: According to a bombshell report in the New York Times, Anthropic co-founder C