Tag: llm

All the articles with the tag "llm".

• Your LLM can't hallucinate a number it was never given

  18 Jul, 2026·3 min read

  Preventing invented facts in the code that builds the prompt rather than in its instructions: no raw numbers, no empty fields, and opaque references instead of names.

• Cache the prompt, not the inputs

  27 Jun, 2026·2 min read

  An LLM cache keyed on a hand-picked list of inputs fell behind the prompt it protected. Hashing the rendered prompt fixed it, and the choice of hash turned out to be a security decision.

• Keep the model call off the request path

  4 Apr, 2026·3 min read

  A per-instance throttle limited nothing and blocked the job meant to recover from quota exhaustion. Removing the request path's ability to generate fixed both.