WeWorkBuddy

[程序员] 为什么我感觉 TPS 比所谓的基模能力还要强

因为某个问题在知名蓝色论坛跟人评论聊天 我说我越来越受不了 gpt 的雷霆大思考了,所以我宁愿回退 sonet+deepseek 也无法认识 Astra 了。 但是下面评论都指责我说模型能力才重要,速度无所谓??? 我搭配了 n 个 agent,多个账号,同时并行了 7 个任务,频繁的等待让我额外付出大量的焦虑切换不同的 seesion(慢也是多账号的原因),我觉得 super agent 解决不了以前,我必须要求够快.... 是只有我这么想么...

Read original source
Source reference for [程序员] 为什么我感觉 TPS 比所谓的基模能力还要强. Screenshot not yet available.
Source record · preview pending · www.v2ex.comOpen the source for the full page.

Source record

Research analysis

Source record

Source account: 因为某个问题在知名蓝色论坛跟人评论聊天 我说我越来越受不了 gpt 的雷霆大思考了,所以我宁愿回退 sonet+deepseek 也无法认识 Astra 了。 但是下面评论都指责我说模型能力才重要,速度无所谓??? 我搭配了 n 个 agent,多个账号,同时并行了 7 个任务,频繁的等待让我额外付出大量的焦虑切换不同的 seesion(慢也是多账号的原因),我觉得 super agent 解决不了以前,我必须要求够快.... 是只有我这么想么...

Available context

Recent records to compare: “Microsoft makes Word, Excel, and PowerPoint generally available inside Copilot, which Satya Nadella calls “the new OS for work” in his Ignite keynote ” (Techmeme, Nov 18, 2026); “KPMG uses 100+ AI agents to conduct a parallel audit of a FTSE 250 company in a pilot, saying the AI asked “better questions” and dug deeper than huma” (Techmeme, Nov 18, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.

Research status

This record has not been assigned a sufficiently supported main content category. No commercial or performance conclusion is generated.

Missing evidence

The main event, affected audience and supporting primary source need review.

Next step

Read the original and identify the decision it supports before choosing an analysis framework.