[Question] Do we have ter­minol­ogy for “heuris­tic util­i­tar­i­anism” as op­posed to clas­si­cal act util­i­tar­i­anism or for­mal rule util­i­tar­i­anism?

[Question] Is there a tax­on­omy & cat­a­log of AI evals?

[Question] Is there an analogue of Rie­mann’s map­ping the­o­rem for split com­plex num­bers, or oth­er­wise?

[Question] How did you get started in mechanis­tic in­ter­pretabil­ity? What other paths have you seen work?

[Question] Why are FICO scores effec­tive?

[Question] Are there ex­am­ples of com­mu­ni­ties where AI is mak­ing epistemics bet­ter now?

[Question] How do you read Less Wrong?

[Question] How does one tell apart re­sults in ethics and de­ci­sion the­ory?

[Question] Han­dover to AI R&D Agents—rele­vant re­search?

[Question] Is SGD ca­pa­bil­ities re­search pos­i­tive?

[Question] What is the (LW) con­sen­sus on jump from qualia to self-aware­ness in AI?

[Question] High-Re­sis­tance Sys­tems to Change: Can a Poli­ti­cal Strat­egy Ap­ply to Per­sonal Change?

[Question] Shouldn’t tak­ing over the world be eas­ier than re­cur­sively self-im­prov­ing, as an AI?

[Question] Why there is still one in­stance of Eliezer Yud­kowsky?

[Question] Thresh­olds for Pas­cal’s Mug­ging?

[Question] Why Would we get In­ner Misal­ign­ment by De­fault?

[Question] How Im­por­tant is In­vert­ing LLMs?

[Question] How valuable is money-in-mar­ket?

[Question] Why is OpenAI re­leas­ing prod­ucts like Sora and At­las?

[Question] Fi­nal-Exam-Tier Med­i­cal Prob­lem With Hand­wavy Rea­sons We Can’t Just Call A Li­censed M.D.