Ex-Claude superfan: getting the best from Astra/Sol requires relearning how you prompt
mariofilhoml · x · 2026-11-19
A self-described former diehard fan of Sonnet/Opus shares that if you really want the best out of Astra/Sol, you have to spend time learning how to talk to it — the way you prompt GPT is not the same way you prompt Claude. The takeaway: the new model family's interaction style differs materially from existing ones, and old prompting habits transfer poorly.
More from coding & agent
- New TLAPS-Bench blog: formally proving correctness of real-world system specs with TLA+ — tianyin_xu · 2026-11-19
- Pierre releases Words, a streaming Markdown parser 2x faster than md4x and 20x faster than Streamdown — andersonbcdefg · 2026-11-19
- Rivet's lesson: JEV doesn't reason—split severity classification into tiny yes/no prompts — yawnxyz · 2026-11-19
- 16x Microsoft MVP demos a native PowerShell agent built on Microsoft's Intelligent Terminal — dfinke · 2026-11-19
- Musk: Treat Grok Bot like a really smart employee, says most users underuse it — elonmusk · 2026-11-19
- Eve agent tool cuts build time 8x to 6.9s by reusing compiler module graph — evilrabbit_ · 2026-11-19