dlwh: We optimized the legible version of our goals — and forgot the computation we meant to speed up
dlwh · x · 2026-10-16
- dlwh argues that formalization, originally motivated by faster computation on real machines, became a research objective divorced from that original goal.
- He frames this as a general problem with AI and most institutions: we optimize the legible version of what we want, then are surprised when it isn't the same thing.
Related event: dlwh: Optimizing Legible Goals Loses Sight of the Original Aim(2 posts)→
More from AGI Musings
- AI circles debate whether a recent PhD signals poor judgment as credentials lose meaning — repligate · 2026-10-16
- Debate: relational preferences — AI that terminally wants to obey — as an alignment bet — teortaxesTex · 2026-10-16
- Sabine Hossenfelder fires back: academia's impact metric turned physics into a paper mill — skdh · 2026-10-16
- Researcher credits GPT for multiple accepted papers, incl. disproving Wegner's 1965 conjecture — ctjlewis · 2026-10-16
- Ideas no longer have a waiting period: agents can build them as soon as they're articulable — akbirthko · 2026-10-16
- Ex-researcher: labs willing to cheat/distill ship great models faster than those building self-sufficient stacks — _aidan_clark_ · 2026-10-16