Qwen trained to continuously refit happiness probes
Sauers_ · x · 2026-11-09
A brief observation that Qwen has been trained to continuously maximize and refit "happiness probes" — internal representations repeatedly aligned to an emotion/preference direction. The post is minimal, stating the phenomenon with a link.
More from Models
- User says Terra Max's batch browser use is the main reason for their ChatGPT subscription — amplifiedamp · 2026-11-09
- DeepSeek V4.1 Flash 1017 hits 1,000 tok/s on Vercel while a home 4x 3090 rig does 65 — AccBalanced · 2026-11-09
- Fastino open-sources GLiDE decision models: 27B scores 72.49 on Decision Index at 112ms — RobertTLange · 2026-11-09
- Grok usage limits reset within hours after Musk-led engineering review — XFreeze · 2026-11-09
- Qwen4-27B leaks questioned: 480 tps benchmark may be Qwen4-Max-preview on low batches — teortaxesTex · 2026-11-09
- The 'Jensen loves Chinese models' joke: not the LLMs everyone assumed — haider1 · 2026-11-09