AI

Applied to Sideloading: creating a model of a person via LLM with very large prompt by TagWrong 2h ago

Applied to Neuroscience of human social instincts: a sketch by TagWrong 3h ago

Applied to LLM chatbots have ~half of the kinds of "consciousness" that humans believe in. Humans should avoid going crazy about that. by TagWrong 15h ago

Applied to Don't want Goodhart? — Specify the variables more by Yan 19h ago

Applied to Aligning AI Safety Projects with a Republican Administration by TagWrong 21h ago

Applied to The Three Warnings of the Zentradi by TagWrong 1d ago

Applied to OpenAI's CBRN tests seem unclear by TagWrong 1d ago

Applied to Dangerous capability tests should be harder by TagWrong 1d ago

Applied to AI #91: Deep Thinking by TagWrong 1d ago

Applied to DeepSeek beats o1-preview on math, ties on coding; will release weights by TagWrong 2d ago

Applied to Expected Utility, Geometric Utility, and Other Equivalent Representations by StrivingForLegibility 2d ago

Applied to How can we prevent AGI value drift? by Dakara 2d ago

Applied to China Hawks are Manufacturing an AI Arms Race by TagWrong 2d 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 3d ago