Jev 候补名单开始批量放行
TypeSafe 官方更新访问进度:已向一批候补用户发送邮件,并表示会继续放行更多申请者。
OpenRouter 使用 Ori Eval 在评判任务上测试 TypeSafe AI 的 Jev 决策模型,结果显示 Jev 比次快模型快 5 倍以上,最慢请求也优于其他模型的中位数。
1/ Jev, a decision model by @typesafeai, sparked a burst of projects and discussion. We tested it using Ori Eval against popular LLMs on OpenRouter at judging. Jev was >5x faster than the next fastest model, and even its slowest requests beat every other model's median.