jev-as-llm
damienen/jev-as-llm
TypeSafe's Jev, a judgment model that was never trained to write, made to chat one word at a time. Browser-only, bring your own OpenRouter key.
TypeScript
- 星标
- 0
- 派生
- 0
收录依据
实验聊天通过重复 Jev 多选调用逐词拼接文本,展示候选概率,并支持无密钥回放已记录的运行。
damienen/jev-as-llm
TypeSafe's Jev, a judgment model that was never trained to write, made to chat one word at a time. Browser-only, bring your own OpenRouter key.
实验聊天通过重复 Jev 多选调用逐词拼接文本,展示候选概率,并支持无密钥回放已记录的运行。
Measured: asking TypeSafe Jev N questions in one call bills the state once. 2,976 real requests, raw data, exact billing check.
共同主题: openrouter
Local playground and test bench for TypeSafe's Jev System One model: typed questions, calibrated-probability answers, and side-by-side comparison with an LLM baseline.
共同主题: openrouter
Interactive playground for testing Jev model-routing decisions against OpenRouter models
共同主题: openrouter