Hands-on with GPT 6.2 astra and sol: not an Opus 5.5 drop-in, but 'really good' once you adapt
alexcovo_eth · x · 2026-11-19
After a full day on real projects, dev @kunchenguid's review:
- Verdict: GPT 6.2 astra and sol aren't drop-in replacements for fable 5.2 / Opus 5.5, but are 'really good' once you learn their strengths.
- The 'GPT smell' persists: poor judgment on when to ask vs. act — escalating trivial decisions while unilaterally making major tradeoffs.
- Weak as a primary driver: close to Opus 5 for talk-to-it-about-everything workflows, far behind Opus 5.5.
- Highlight: sol's ultrafast mode is 'completely insane' — a real edge when speed matters.
More from Models
- Abacus AI open-sources uncensored Smaug, a 27B model aimed at agentic work — bindureddy · 2026-11-19
- GAO audit finds Claude, Grok, ChatGPT and Gemini safeguards easily bypassed — midwoodgirl10 · 2026-11-19
- Harmonic's Aristotle rewrites Bitcoin Core's C signature parser in Rust with a formal proof — satnam6502 · 2026-11-19
- GPT-6.2 Astra users note it can work 30 minutes without any progress updates — Angaisb_ · 2026-11-19
- Arena points readers to the live Agent Arena Index and its methodology — arena · 2026-11-19
- LMArena launches six new agent indexes; Claude Fable 5.2 tops Work, Coding and Chat — arena · 2026-11-19