Hands-on GPT 6.2 review: Astra and Sol are great, but no drop-in replacement for Fable 5.2 or Opus 5.5
kieranklaassen · x · 2026-11-19
After a full day using GPT 6.2 Astra and Sol on real projects, developer @kunchenguid published a detailed hands-on review that others are amplifying:
- Verdict: not a drop-in replacement for Fable 5.2 or Opus 5.5, but "really good" once you learn to play to their strengths; Sol's Ultrafast mode is a delight.
- The "GPT smell" persists: poor judgment on when to ask the user versus proceed autonomously — escalating trivial decisions while making significant tradeoffs unilaterally.
- Takeaway: adapting your workflow matters more than swapping models.
Reviewers also flagged adversarial code review as a standout strength of the new models.
More from coding & agent
- Open-source MCP server controls Logitech Harmony hubs locally with LLM-safe guardrails — SDNick484 · 2026-11-19
- Study: given an empty computer, strong models write their own games to self-improve — CatAstro_Piyush · 2026-11-19
- AWS case study: Social Department's QuickSearch finds memeable moments across video libraries — AWS ML Blog · 2026-11-19
- Elicit on agent swarms: pharma winners of 2036 will robustly deploy them without going rogue — jungofthewon · 2026-11-19
- Suno MCP now open to all: author makes a full music video via Claude lyrics and Claude Code editing — minchoi · 2026-11-19
- PromptMaker: open-source local prompt studio for SD workflows, runs on 8 GB GPUs — ChanceLingonberry170 · 2026-11-19