AI

Applied to AXRP Episode 10 - AI’s Future and Impacts with Katja Grace by Raymond Arnold at 1d

Applied to Examples of human-level AI running unaligned. by Oliver Habryka at 1d

Applied to [AN #157]: Measuring misalignment in the technology underlying Copilot by Oliver Habryka at 1d

Applied to Re-Define Intent Alignment? by Oliver Habryka at 2d

Applied to Jaynesian interpretation - How does “estimating probabilities” make sense? by Haziq Muhammad at 3d

Applied to Reward splintering for AI design by Oliver Habryka at 3d

Applied to Entropic boundary conditions towards safe artificial superintelligence by Raymond Arnold at 4d

Applied to An examination of Metaculus' resolved AI predictions and their implications for AI timelines by Oliver Habryka at 4d

Applied to In search of benevolence (or: what should you get Clippy for Christmas?) by Oliver Habryka at 5d

Applied to Some thoughts on David Roodman’s GWP model and its relation to AI timelines by Oliver Habryka at 5d

Applied to Work on Bayesian fitting of AI trends of performance? by Oliver Habryka at 5d

Applied to Is the argument that AI is an xrisk valid? by MACannon at 6d

Applied to Any taxonomies of conscious experience? by jacobjacob at 6d

Applied to A model of decision-making in the brain (the short version) by jacobjacob at 6d

Applied to A Models-centric Approach to Corrigible Alignment by Oliver Habryka at 7d

Applied to Equivalent of Information Theory but for Computation? by Oliver Habryka at 7d

Applied to (2009) Shane Legg - Funding safe AGI by Oliver Habryka at 7d

Applied to Bayesianism versus conservatism versus Goodhart by Oliver Habryka at 8d

Applied to [AN #156]: The scaling hypothesis: a plan for building AGI by Oliver Habryka at 8d

Applied to Benchmarking an old chess engine on new hardware by Oliver Habryka at 8d