There are a few things I like about Sol:
1. It's much faster, especially for tasks that don't involve internet search or complex skills—the speed improvement is quite noticeable.
2. It's less verbose (which is also one of the reasons it feels faster).
3. Codex is great!!!
Or… what if we gave you $100 in Codex credits if you tell us what you love about GPT-5.6 Sol or why you switched?
Tweet it, claim your gift, enjoy more usage. First 10k get the free tokens!
https://t.co/8mU93eA13i
@Freerunnering 我也是这样做的,我为那个目标任务写了计划文档的,但是在第一次压缩之后,Sol 还是重新做了之前的最后一个任务——当然这个任务确实和后面的目标任务有关联,但无论如何不应该重复做一遍。这看起来就像是压缩以后 Sol 忘了这个独立任务是不是还没做或者它是不是和后面的目标任务有关联需要重复之类的。
OpenAI have done a great job fixing the compaction problem. Codex 5.6 Sol can work for a really long time and still stay on task, and not forget things or get lost.
It's impressive how much I don't really think about or worry about context length anymore.
OpenAI have done a great job fixing the compaction problem. Codex 5.6 Sol can work for a really long time and still stay on task, and not forget things or get lost.
It's impressive how much I don't really think about or worry about context length anymore.