WHAT NEW IN X11.02 MON

X 上的 AI 合集档案 · 22 个合集 · 65,263 条

gpt-6POST

用户对比 Opus 5.5 与 Astra:Astra 额度撑不住

一位用户说用了 Opus 5.5 后觉得 ChatGPT 模型很原始,Sol 6.1 要反复纠正,Astra 虽好但额度难以持续使用。

Irushi
@Im_IrushiK23 天前收录原推发布于 2026.10.09
Irushi @Im_IrushiK原推发布于 2026.10.09
在 X 上打开原推

After using Opus 5.5 since launch, ChatGPT models are starting to feel so primitive The difference isn't just intelligence. It's how well Opus understands what you want without needing constant guidance. With Sol 6.1, I keep having to explain, correct, and iterate. Opus 5.5 just seems to get it, and the creativity is on another level. And the crazy part? On the $20 plans, both can burn through a 5-hour limit pretty quickly, but I get so much more actual work done with Opus. Astra is great, but the usage makes it hard to use sustainably. Atpt, Sol feels more like a subagent compared to Opus 5.5.😭😭LOL Anyone else feeling this difference?

x.com/im_irushik/status/2108423349571629074采集于 2026.10.10 10:02