TypeSafe AI 的 Jev 模型在安全审查任务中表现优异
We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety rev...
TypeSafe AI 的 Jev 模型在安全审查任务中表现优异，其 p95 延迟比 GPT-3.5-Luna 快 18 倍且更准确。该模型已集成到 Vercel AI Gateway 中，并可能成为默认设置。
TypeSafe AI 的 Jev 模型在安全审查任务中表现优异，其 p95 延迟比 GPT-3.5-Luna 快 18 倍且更准确。该模型已集成到 Vercel AI Gateway 中，并可能成为默认设置。
We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety rev...
We're seeing extraordinary results from @typesafeai . Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default. Pranit @fazxes We benchmarked fx auto mode (safety) classifier with @typesafeai 's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice 🔗 View Quoted Tweet 💬 3 🔄 1 ❤️ 45 👀 2348 📊 6 ⚡
