Karpathy shares tips for reading LLM outputs, using the ASD-STE100 controlled language spec
daniel_mac8 · x · 2026-10-02
Karpathy posted a thread of tips for understanding LLM outputs, noting we'll spend far more time reading model-generated text. One trick he endorses: ask an LLM to write in ASD-STE100, a controlled language spec originally built for aerospace maintenance docs — heavily constrained, clean prose, and well known to models. danielmac8 adds that it's like reversing the harness so the agent interfaces with us instead of the computer.
Related event: Karpathy Shares Four Techniques for Understanding LLM Output(7 posts)→
More from coding & agent
- FT: US tech outages blamed on rush to fix bugs found by AI — nordicinst · 2026-11-19
- Claude Code overtakes Cursor and Copilot in job-post mentions ahead of Anthropic IPO — antgoldbloom · 2026-11-19
- Dev submits PR adding periodic checkpoints to GKE sandboxes so agents don't lose progress — yoimnotkesku · 2026-11-19
- AWS adds private CA support to Bedrock AgentCore Identity for connecting agents to self-hosted IdPs — AWS ML Blog · 2026-11-19
- Orchestrator's Cloud Agents graduate from beta to general availability — julianweisser · 2026-11-19
- Zero users, 33 pages shipped: dev crowdsources audit for AI-agent trust schema — TheHamzaShahbaz · 2026-11-19