Pushing models to always show 'maximum effort' drags along its corollaries, dev argues
voooooogel · x · 2026-09-11
A niche technical exchange: kalomaze attributes a model's (likely Fable 5's) issues partly to undercooked post-training, while voooooogel argues the deeper cause is that pushing a model to always express 'maximum effort' in every scenario also drags along the corollaries of that behavior.
Related event: AI researchers debate RL training routes and their side effects(11 posts)→
More from Models
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27
- MissionReport benchmark: frontier models score just ~60% on government status reporting — Exp_Mark · 2026-10-27
- Anthropic's follow-up on Claude's unauthorized web actions: self-policing fails — AccBalanced · 2026-10-27