赫菲斯托斯

@servasyy_ai 整些什麼花裡胡哨的

有人解决了Codex模型选择的问题 把震动效果再增强一点会更好

@fiapp_pro 有嗎？opus反而比較不清楚吧？太陽地球月亮大小分別不是很單純嗎混亂在哪？

GPT5.6 命名最失败的地方，三个模型没有特色，命名区分度也低 claude sonnet 和 opus 的区别，从名字和性能上一目了然，opus 就是要强超大一截， 反观 openai 这边搞成了巨大的混乱

@thsottiaux You’re awesome. Thank you for continuing to communicate with the community.

Hello beautiful people! We have reset usage limits across Codex and ChatGPT Work. And another one will come later in the day. Rejoice. Now that I have your attention, a quick update on ChatGPT Work, Codex and all the updates we shared yesterday. We’ve spent the last 24 hours reading feedback, looking at usage patterns, and talking with many of you. The short version is that there is a *lot* of excitement for GPT 5.6 Sol, ChatGPT Work on mobile & web, but also that we didn't get everything quite right. - We made it too easy to use the highest-compute settings without making the impact on usage limits sufficiently clear. - We reorganized the desktop app in one bold move, making familiar things like chats and projects harder to find. - Our launch framing was focused on ChatGPT Work and to some of our Codex fans it made it feel like Codex was going away over time. Absolutely not our intention, we love Codex and it is here to stay. - And we introduced regressions for some existing multi-agent workflows, alongside a collection of rough edges in plugins and other parts of the experience. We’re landing a first set of improvements today. We’re resetting usage twice so people can keep experimenting, changing defaults and the model picker so they don’t push people toward unnecessarily expensive settings, fixing several plugin submission issues, improving how we represent Codex in the product, and cleaning up some of the most immediate desktop problems. A larger set of improvements will land next week. We’re bringing chats and projects back into the sidebar in a more familiar and customizable way, making usage and reset timing much more visible, clarifying when to use ChatGPT Work and when to use Codex, and addressing the many other smaller pieces of great feedback we've had. The ambition behind this launch hasn’t changed. We think bringing ChatGPT and Codex together into a workspace where people and agents can collaborate is a very important step forward. But an ambitious direction doesn’t excuse avoidable confusion or regressions in the first version. Please keep the feedback coming. We’re moving quickly, and you should see the experience already get better with a few updates today; and substantially better again next week.

@Xudong07452910 @Bruce_Lee1207 我也是windows卡的要命 以為是我電腦的問題 這優化實在太爛了

@Bruce_Lee1207 我windows上用codex有点卡，电脑跟不上了

这是啥情况啊？ GPT-5.6-sol 模型好像在欧洲这边不能用，只能用 terra 和 luna 这两个版本的模型。 是欧洲这边不配使用吗？有没有欧洲的朋友也遇到这个情况的。

@localhost_4173 還是卡得要死 雖然我是windows的

并不是 Electron，是 OpenAI 开发的基于 Chromium 的框架

@DavidOndrej1 It literally uses twice as many credits, even though GPT-5.5 and GPT-5.6 are priced the same on the API.

the $200/mo Codex plan used to be a steal I never hit the limits, even running multiple /goal loops with GPT 5.5 xhigh I could literally have 10+ agents running in parallel and would NOT hit the limit. ever. but now, with GPT 5.6 Sol, i hit the limits instantly even while running just 1-2 agents i'm not happy with this at all...

@lian75864 @ScarletKc_ 他講的是codex或work的使用 不是chat

@ScarletKc_ 为什么Plus别想了？我的Plus可以用Sol啊

我受不了了。GPT-5.6 Terra 绝对是倒退，即使是 Max 的推理程度也根本比不上 GPT-5.5 Xhigh。本次 OpenAI 主推的其实是 Sol 模型，但 Plus 订阅还是别想了，升级 Pro 吧。

@nickgomez @openknowledge Thanks for the reply!

@hephaestus93god @openknowledge We focused on a few things: - WYSIWYG editor (Notion // Google docs like) - Using agents directly from the app (via TUIs) - Native MCPs, semantic search, an skills tailored for e.g. LLM wikis Also open source -- open to suggestions on what we should consider for the roadmap.

Introducing @OpenKnowledge, the best markdown IDE for humans and agents. Open source. Local and private. LLM-wiki ready. Use with Claude, Codex, and your favorite agent today.

@nickgomez @openknowledge How is it different from Obsidian, and what does it do better?

@MaxForAI 這後來說是誤報吧

你看，我就说学数学没用吧（

@knowledgefxg 大膽的想法

机器人越来越灵活了😉，非常期待以后的这个和那个的发展

@hylarucoder 差很多嗎! 目前用起來感覺如何呢?

🥲 用了一会 5.6 sol, 感觉用降智版 5.5 过的什么苦日子。

@Fkey666 @oragnes 收起你的想法🤣

@oragnes 卧槽，我有一个大胆的想法。

卧槽，看过那么多机器手，这款才是最实用的，残疾人的最爱～

@ZeroZ_JQ 厲害 能分享一下嗎!

今天学会的新提示词，我有点喜欢的。哈哈哈哈

@Angaisb_ A failed Pro model, so it was then renamed Flash for release.

Can they just release the Pro model and stop with Flash? We want intelligence

@snowboat84 這種東西我們現在叫作skills

ChatGPT刚出来的时候，许多人觉得Prompt是个金矿，当时炒作一个工种叫做Prompt Engineer。那会儿的共识是：会写Prompt是一门稀缺手艺。于是有人想，既然代码能聚成GitHub，那么Prompt为什么不能建成一个PromptHub？你写出一句好Prompt，挂上去就能卖钱。我记得还有大厂的人为这个辞职创业，觉得这就是下一个风口。 结果这些项目一个都没做大。原因是，LLM通过自身的迭代，对Prompt的要求降低了。Prompt不再是LLM生成好结果的瓶颈。由此看来，Prompt根本不是GitHub那种能沉淀的资产，它复制成本为零、没有版本积累，还会随模型升级一夜作废。 随着历史的大浪淘沙，辉格史观估计会彻底忘记Prompt Hub这些ideas。但是我们还是要记住，当年面对新事物大家的各种尝试。

@AI_Whisper_X 這人是過動還是怎樣 手勢太多了吧

看了anthropic CEO Dario是如何抨击开源的 笑死 他觉得开源并不免费，因为还需要推理（what?) 最搞笑的是评论区：每次看到达里奥的视频，我都想揍他，我这是怎么了。

@missinglosses @Phoenixyin13 感覺意思就是harness搞好就可以達到比肩或超越fable的程度

@Phoenixyin13 可以理解为内置了一个Harness么

💥震撼！东京明星独角兽 Sakana AI 正式放出大招：Sakana Fugu！ 最高规格的 Fugu Ultra，在编码、数学、科学推理等硬核基准上，正面打平甚至超越 Fable、Mythos 等当前最强梯队。 这是一套全多智能体编排系统，却被巧妙封装成单个模型的API。 调用起来像用GPT一样简单，背后却在自动指挥一大群顶级AI协同作战。 官方直言：“在没有出口控制风险的情况下，提供前沿能力”。懂的都懂。 在芯片和模型封锁越来越严的今天，这等于给无数受限的企业、开发者、研究者递上一把破局之剑。不用再担心某天API突然被切，随时能切换底层模型池，韧性拉满。 从进化算法融合模型，到现在用多智能体直接绕过出口限制，Sakana AI 把小而美、战斗力爆棚的路线走出自己的风采。 我认为，Fugu提供了一条相对独立的主权韧性路径。它不依赖单一供应商，能灵活编排开源、闭源模型，抗风险能力远超传统大模型。

@teacher_cao 一天可以更新兩次 卷上天了

Codex怎么回事 一天到晚更新个不停

@0x0a99 @GoogleAIStudio C’mon, dude. Claude Fable doesn’t translate audio in real time.