Prompting LLMs with ASD-STE100 aerospace spec yields cleaner output, devs share tips
blixt · x · 2026-10-03
Karpathy notes we'll spend more time understanding LLM outputs and suggests asking models to write in ASD-STE100, a controlled language spec for aerospace maintenance docs with strong constraints on clean writing.
User blixt adds a practical twist: prompt with "follow ASD-STE100 guidelines but don't veer away from well-established technical terms in the repo" — the second half matters a lot. He also shares building his own harness where letting the AI create inline interactive experiences like diagrams works well.
Related event: Karpathy Shares Four Techniques for Understanding LLM Output(7 posts)→
More from coding & agent
- Fewer, well-designed agent harnesses beat sprawling agent fleets, argues vixsheikh — annetgriffin · 2026-10-26
- Agent memory explained in 12 minutes: working, procedural, semantic and episodic — _AustinCalvert_ · 2026-10-26
- Grok Bot v0.75.5 leak touts stored cards, email forwarding, 3x automation limits — mark_k · 2026-10-26
- Every time my agent breaks my UI, I add a rule to its skill — 10 design laws — _AustinCalvert_ · 2026-10-26
- Turn nouns into verbs: the 'Range' trick to unlock cross-domain AI output — petesena · 2026-10-26
- Prompt like a top expert: set extreme bars, real tools, and outside judges — petesena · 2026-10-26