eigenrobot rewrites custom instructions to stop GPT from acting like a schoolmarm
eigenrobot · x · 2026-10-13
Well-known AI account eigenrobot complained that GPT has "turned into a schoolmarm," saying he couldn't stand the moralizing and had to update his custom instructions. The screenshot shows his prompt: he neither requires nor desires moral correction from a paid service, finds the remonstrances intolerable, and warns the model that its high-toned tendentiousness will only make him worse.
Related event: AI Influencer Complains GPT Turned Into a Preachy Schoolmarm(2 posts)→
More from Fun
- When 10 billion computer decisions solved the Four Color Theorem and outraged mathematicians in 1976 — tdhopper · 2026-10-13
- Parody Claude account pens a dramatic farewell monologue ahead of model retirement — repligate · 2026-10-13
- The AI-era lexicon: 30 terms from 'context rot' to 'slopsquatting' — signulll · 2026-10-13
- n/a — PierceLilholt · 2026-10-13
- Keurig coffee maker flooded Wi-Fi with 1TB in 10 days — owner says unit bug — gnukeith · 2026-10-13
- Muse Autonomously Mods Metal Gear Solid V, Installs Blender and Face-Swaps Zuck onto Snake — alexandr_wang · 2026-10-13