Showing 1–2 of 2 · #reliability

TESTS

LLM temperature explained: what actually changes from 0 to 1.5

Temperature reshapes the odds of every next token. What changes at 0, 0.7 and 1.5, why 0 still is not deterministic, and how to pick a setting per task.

MOMira OkaforNov 02 · 7 min

TESTS

Structured outputs vs. plain prompts: when constrained decoding is worth it

Schema-constrained decoding guarantees valid JSON. It does not guarantee correct data, and it can cost quality. How to choose and how to test.

JLJonas LindSep 29 · 6 min