Teaching a retired pharmacist Claude: model tiers, prompt templates, and the 40-prompt rot
rubenhassid · x · 2026-11-21
A practitioner distills Claude basics into 6 lessons taught to his retired-pharmacist mom: use Fable 5.2 for prompt 1 and hard goals, Opus 5.5 for the real work; copy-paste a goal/context/limits starter prompt; chain models in separate chats ($0.15 for 2 prompts vs $14 for 40 on Fable); watch for quality rot at 40 prompts and 100-prompt cutoff; edit the prompt instead of arguing; and a banned-words anti-AI-style skill.
More from coding & agent
- Pro-tip: pair your agent with a second agent whose only job is to challenge it — craigbalding · 2026-11-21
- Dev runs Gemini coding all day without hitting Pro limits; agent nails sound design — lipeng0820 · 2026-11-21
- AI gateways are becoming the key control layer in production AI stacks: 8 capabilities — goyalshaliniuk · 2026-11-21
- Mnemos 2.0: agent memory designed to preserve what matters for the next session — RileyRalmuto · 2026-11-21
- InferenceBench ranks agents on LLM serving speedup: Claude Opus 5.5 tops at 12.08x, agents lose to simple hyperparameter search — maksym_andr · 2026-11-21
- 4 architecture patterns to tame multi-agent system reliability, from a 27-year reliability engineer — bibryam · 2026-11-21