Stop fixing model mistakes — feed AI your taste and context, the only thing that won't be obsolete
chaseleantj · x · 2026-09-25
chaseleantj shares advice from a chat with a friend: don't waste time fixing the mistakes current AI models make — invest in what stays useful when the next model ships.
Concretely: teach the model about you. Have it pull all your previous transcripts and analyze your projects, the decisions you made, what annoys you, and what you're passionate about. When implementation becomes cheap — Opus 6 doing in a day what Opus 5.5 did in a month — technical details stop mattering. Your taste, style, experiences and worldview are the context that makes what you build with AI unique, and that will never be obsolete.
Related event: Feed AI Your Personal Context Instead of Fixing Model Errors(2 posts)→
More from AGI Musings
- Grady Booch: LLMs Only Resemble the Brain at Its Most Primitive Structures — Grady_Booch · 2026-09-25
- AI Agents Will Move Serious Money, But Nobody Has Answered the Liability Question — Master-Sprinkles-848 · 2026-09-25
- Krauss Podcast Chats With Sabine Hossenfelder on AI Breakthroughs, Nightmares, Dark Matter — skdh · 2026-09-25
- Materials PhD Uses AI to Map a Decade of Battery Literature, Questions Reading 100 Papers — Clean-Interview-5081 · 2026-09-25
- Bill Maher drops jokes for first time in 23 years to warn on AI; researcher says pause defeatism is untenable — wfithian · 2026-09-25
- Investor Stewart Alsop: AI agents are shattering an already fragile social trust — StewartalsopIII · 2026-09-25