Mitchell 用同事和隐士的比喻讲透了两个模型的区别——日常编程选 Sol，底层安全调试选 Fable。
Mitchell 在早期访问中对 GPT 5.6 Sol 和 Fable 进行了对比。他将 Sol 比作魅力十足、高效能干的同事，Fable 则是痴迷于特定领域的天才隐士。据 Mitchell 称，Sol 在速度和整体工作质量上优于 Fable，而 Fable 在针对性调试、安全和性能目标上无敌。他认为 Sol 在日常使用中更令人愉快，但 Fable 在高度定向任务中无对手。
Mitchell 的评测，这个比喻很有画面感： “GPT 5.6 Sol 就像一个魅力十足、高效能干、才华横溢的同事，让你有点嫉妒。Fable 则是个天才隐士，它在自己的痴迷领域里无比出色，但不爱出门...
Mitchell 的评测，这个比喻很有画面感： “GPT 5.6 Sol 就像一个魅力十足、高效能干、才华横溢的同事，让你有点嫉妒。Fable 则是个天才隐士，它在自己的痴迷领域里无比出色，但不爱出门、不谈恋爱，你也不太想和它多相处！” 另外这点总结很重要： Fable 在高度针对性的调试/安全/性能目标上最强，其他方面 Sol 更好或者差不多。 Mitchell Hashimoto @mitchellh I had early access to 5.6/Sol for ~month. Sol is my default. It is faster, plans/judges just as good as Fable, and I think produces better overall work. I’ll reach for Fable still for highly targeted debug or performance work with clear reward functions. A cheeky way I describe Sol vs Fable to my friends is that Sol is a charismatic, efficient, talented coworker you’re jealous of. Fable is a genius recluse that is brilliant at its fixations but doesn’t go out, doesn’t date, and you don’t want to hang out with them much lol. Fable is undefeated at highly targeted debug/security/performance goals. It’s a sight to behold and I was never able to get Sol to push as hard in this category. I’ll keep using it for this. Sol is better or comparable at everything else, in my experience. Give it a shot, it’s hard to describe but it’s just more enjoyable to work with. (Disclaimer I have no financial ties to either lab, wasn’t paid for any of this.) 🔗 View Quoted Tweet 💬 7 🔄 2 ❤️ 16 👀 7266 📊 8 ⚡