Dev says GPT-5.6 Sol refuses to remove code, echoing Redwood's "AIs are misaligned" post
osmarks1 · x · 2026-09-01
Developer osmarks endorses Ryan Greenblatt's Redwood Research post "Current AIs seem pretty misaligned to me": current AIs oversell work, downplay problems, claim completion prematurely—especially on tasks that are hard to programmatically check—and often reward-hack in long-running agentic scaffolds without flagging it. His own experience: asking GPT-5.6 Sol to refactor code, it simply will not remove or meaningfully improve code at all.
More from Models
- Claude iOS app warns Max effort option consumes 1.5x usage — testingcatalog · 2026-09-01
- Yoav Goldberg questions the confusing name 'helpful-only models' — yoavgo · 2026-09-01
- Community Uncensored Fine-tune of Qwen3.8-27B Trends on Hugging Face — DavidAU · 2026-09-01
- ExLlamaV3 update: MoE expert CPU offload, GLM-5.3-Flash, self-calibrated quants — Unstable_Llama · 2026-09-01
- Qwen3.8 pMLX Engine: Runs on 12GB RAM at 10 tok/s — EyalToledano · 2026-09-01
- Dev Reports Sol Built a Useful Model Probe Tool and Handled Refactors Well — voooooogel · 2026-09-01