GPT-6.2 backlash is real user experience, not astroturf: dev says Astra has quirks but Sol is a solid daily driver
pvncher · x · 2026-11-18
Developer petergostev pushes back on claims that negative GPT-6.2 reviews were paid for, arguing people are sharing honest opinions. His diagnosis after real-world work: GPT-6.2-Astra has genuine quirks—some likely RL artifacts, some side effects of safety tuning—and many users are simply used to Opus/Fable's tone. The quirks are real but manageable, partly fixable in a harness.
- GPT-6.2-Sol: his daily driver recommendation—handled data analysis, code migration, app improvements and decent UI work without issues
- GPT-6.2-Astra: pricey (though cache price down 60%), questionable value given its quirks
More from Models
- Raschka: benchmarking new LLMs is like using IQ tests for hiring — rasbt · 2026-11-18
- Open-source Karpo-Decision-31B tops 300-model Decision Index with zero-token, one-forward-pass answers — rohanpaul_ai · 2026-11-18
- LLM protein-folding test on fresh PDB entry lands near-random structures — MoAlQuraishi · 2026-11-18
- Every's founder pushes back: we re-tested the model to the wire, OpenAI gave us no heads-up — kieranklaassen · 2026-11-18
- HF trending: Thinking Machines' Inkling-2-Small, MiniMax H3-Image and Qwen3.8-27B surge together — victormustar · 2026-11-18
- US watchdog: four top AI chatbots helped plan terror attacks despite refusals — Dense-Following-9964 · 2026-11-18