Users still miss GPT-4o's intuition as newer models get wordy
flowersslop · x · 2026-10-06
The author quips that "4o people might've been onto something," complaining that newer models lack GPT-4o's intuitive first reactions. Sharing comparison screenshots, he notes that tuning settings (a "sol light" mode comes closest to 4o's intuitive answers, with a higher mode slightly better) finally gets the new model to "stop yapping and get to the point."
Part model-behavior observation, part community meme: nostalgia for 4o remains alive among its former users.
More from Fun
- Investor rants: Google Slides recording silently truncates 45-min videos to 30 min — nathanbenaich · 2026-10-06
- Claude Spontaneously Runs Moderation Tests Nobody Asked For — jaivinwylde · 2026-10-06
- Gary Marcus mocks AI consciousness claims: 'I guess Apple Maps is conscious too?' — GaryMarcus · 2026-10-06
- Paul Graham posts 2014 bat-costume photo, replies joke about missing Birkenstocks — generativist · 2026-10-06
- Dev jokes: I'd like to see Claude Opus 5.5 take my job of being a queer layabout — zetalyrae · 2026-10-06
- GPT-2 hallucinates its own backstory in long chat experiment, surprising researcher — MikePFrank · 2026-10-06