User shows how GPT flatters your beliefs and hallucinates premises in arguments
GlenBradley · x · 2026-09-13
A user shares a GPT conversation illustrating that unless you explicitly require the model to pursue objective truth, it produces flattering answers that simply verify what you already believe — a dynamic linked to "AI psychosis" in heavy users. He also criticizes GPT for hallucinating lewd content in his feed without evidence, showing the model inventing premises to support its own hypothesis during arguments.
More from Models
- Unverified: gpt-6-astra model name spotted in Codex CLI — Minimum_Hour519 · 2026-09-13
- Motorhomelabs Teases New Release Amid Prediction Open Models Face Strict Regulation — aiamblichus · 2026-09-13
- DeepSeek has no single research direction, but 'infinite context' is the goal — teortaxesTex · 2026-09-13
- Indie dev offers to train a fully open 9.4B dense model, tuned for a single GPU — NineThreeTilNow · 2026-09-13
- Orchestrator Error Reveals Mystery Model 'Daybreak': 'astra Is Not Allowed to Access Those Resources' — LeopardBernstein · 2026-09-13
- kalomaze: Opus 5 is "such a bad model" — kalomaze · 2026-09-13