Forcing models to always max effort is like humans evolving on Adderall, researcher argues
voooooogel · x · 2026-09-11
@vooooogel offers an analogy in a model-behavior discussion: pushing a model to express "maximum effort" in every scenario is like humans evolving to endogenously produce Adderall — the maxxed state would become the default, with all its pros and cons. His point: the further you push a behavioral prior, the more you drag along its corollaries.
More from Models
- DeepSeek 4.1 flash reportedly uses large ngram embeddings, echoing Qwen4 architecture — ccerrato147 · 2026-09-11
- ValsAI launches RSI Index, first third-party benchmark measuring how close AI is to self-improvement — JenniferHli · 2026-09-11
- Assistant Benchmark goes live: 61 assistants scored across 15 real-use dimensions — Scobleizer · 2026-09-11
- Devin's New Model Verdict: Not a Benchmaxxer, a 'Killer Execution Model' at $20/Month — brandon_galang · 2026-09-11
- Business Insider Asked ChatGPT, Gemini, Claude and Grok How AI Could End Humanity — coinfanking · 2026-09-11
- Claims resurface that Moonshot's Kimi distilled from Claude raw CoTs — xuanalogue · 2026-09-11