AI

Applied to Don't want Goodhart? — Specify the variables more by YanLyutnev 3h ago

Applied to Aligning AI Safety Projects with a Republican Administration by TagWrong 4h ago

Applied to The Three Warnings of the Zentradi by TagWrong 6h ago

Applied to OpenAI's CBRN tests seem unclear by TagWrong 9h ago

Applied to Dangerous capability tests should be harder by TagWrong 9h ago

Applied to AI #91: Deep Thinking by TagWrong 12h ago

Applied to DeepSeek beats o1-preview on math, ties on coding; will release weights by TagWrong 1d ago

Applied to Expected Utility, Geometric Utility, and Other Equivalent Representations by StrivingForLegibility 1d ago

Applied to How can we prevent AGI value drift? by Dakara 1d ago

Applied to China Hawks are Manufacturing an AI Arms Race by TagWrong 1d ago

Applied to A Little Depth Goes a Long Way: the Expressive Power of Log-Depth Transformers by TagWrong 2d ago

Applied to Why Don't We Just... Shoggoth+Face+Paraphraser? by TagWrong 2d ago

Applied to U.S.-China Economic and Security Review Commission pushes Manhattan Project-style AI initiative by TagWrong 2d ago

Applied to Intrinsic Power-Seeking: AI Might Seek Power for Power’s Sake by TagWrong 2d ago

Applied to AISN #44: The Trump Circle on AI Safety Plus, Chinese researchers used Llama to create a military tool for the PLA, a Google AI system discovered a zero-day cybersecurity vulnerability, and Complex Systems by Corin Katzke 2d ago