Perplexity 用提示引导自蒸馏训练 Computer 模型从错误中学习
Super cool!
精选理由
Perplexity 分享了怎么让 Computer 模型从自己的错误里学习，A/B 测试里工具调用失败率降了 21.2%，做法挺值得看看的。
Perplexity 公布了一项新研究，他们采用 hint-guided self-distillation（提示引导自蒸馏）方法对 Computer 模型做后训练，让模型从自身错误中学习。在一次线上 A/B 测试中，较晚训练的 checkpoint 相比较早的 checkpoint 将工具调用失败率相对降低了 21.2%。
原文 · Suhail
Super cool!
Super cool! Perplexity @perplexity_ai New research: We post-trained a Computer model to learn from its own errors using hint-guided self-distillation. In a live A/B test, a later trained checkpoint reduced tool-call failures by 21.2% relative to an earlier checkpoint. 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 4 👀 2054 📊 1 ⚡
