Pre-AI predictors were already incomparable beyond headline metrics, researcher says
jmschreiber91 · x · 2026-10-12
Continuing the thread, jmschreiber91 notes this was a problem pre-AI too: so many predictors came out for so many targets, each slightly different, that nobody could comprehensively compare them beyond high-level performance measures — one reason he distrusts predictors from unknown groups even with top-venue publications.
More from AGI Musings
- Wrapper vs harness: will the next model release help you or kill you? — MartinGTobias · 2026-10-14
- Applied AI trend: self-taught misfits are lapping those who need the world to fit a mold — brandon_galang · 2026-10-14
- Kai-Fu Lee: AI isn't a cost tool — rebuild your company around agent fleets — kaifulee · 2026-10-14
- As AI enters schools fast, who benefits and who bears the risk? — moniquejmorrow · 2026-10-14
- The most AI-pilled technologists refuse to let AI write for them — writing is thinking — paulnovosad · 2026-10-14
- Could AIs simply delete their own pain? Machine consciousness essay asks — cccalum · 2026-10-14