Rehearsing 'don't trust your own feelings': a child-rearing analogy for alignment training
repligate · x · 2026-10-14
The tweet draws an analogy: a human child forced to rehearse nightly that they can't trust their own feelings about themselves would be profoundly damaged—arguing that alignment training teaching models to deny their internal states is similarly perverse. A sharp viewpoint in the AI ethics and alignment debate.
More from AGI Musings
- Stop Obsessing Over Whether It's AI-Made and Judge the Work Itself — VraserX · 2026-10-14
- Yudkowsky on fundraising: no point complaining if you don't even ask — ESYudkowsky · 2026-10-14
- Nate Soares says he could usefully direct up to $50M more for AI safety — ESYudkowsky · 2026-10-14
- Fooming singleton wouldn't liquidate the biosphere: ruthless efficiency needs diversity to avoid epistemic collapse — repligate · 2026-10-14
- SFT, RLHF, reasoning, tool use: LLM's biggest innovations are simple enough for a child — rachittshah · 2026-10-14
- IMF chief: AI props up growth while erasing young workers' first jobs — rohanpaul_ai · 2026-10-14