Simon Willison·· 6 h ago
llm-echo 0.5
llm-echo 0.5
AI summary
Release: llm-echo 0.5 I'm working towards a new LLM release, and testing PRs caused me to revisit the llm-echo debug plugin. This plugin provides a "model" which doesn't involve an LLM at all - it just repeats back the prompts that have been fed to it.
Selection record
Threshold 76Media and individualsFirst 18Second 12
Not admittedSum of both 30 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：LLM调试插件更新，涉及模型与token计数
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Simon Willison · simonwillison.net