joe sai

独立开发者

[joe sai @_blue_sweater_]

测试一下了，GPT 5.6 Sol，最高推理强度 ，1.5倍速。一次调用就消耗了20%的5h使用量。 这是$200的套餐🤯

[joe sai @_blue_sweater_]

发现了个很影响专业感的显示bug

[OpenAI @OpenAI]

Sol, Terra, and Luna, our GPT‑5.6 family of models, are starting to roll out now in ChatGPT, Codex, and the API.

[joe sai @_blue_sweater_]

🫡过年了

[joe sai @_blue_sweater_]

@Lonely__MH 已经被封完了哈哈哈🥲

[Ankur | NoCode Talks @NocodeTalks]

Created this video in just 20 minutes.

One thing I've noticed with HyperFrame + Claude is that if you understand the technical aspects of video creation, it's much easier to generate the results you want.

For this video, I simply asked it to create a storyboard-style whiteboard animation with a handwritten effect and a hand appearing as it writes, while explaining the concept I wanted to cover.

If I don't explicitly mention the storyboard/whiteboard style, I'll end up prompting over and over again and still won't get the video I'm looking for.

[joe sai @_blue_sweater_]

@ftium4real 需要等一段时间吗？

[OpenAI @OpenAI]

Introducing a limited preview of GPT-5.6 Sol, our next generation frontier model, as well as GPT-5.6 Terra, a balanced model for efficient, everyday work, and GPT-5.6 Luna, a fast and affordable model for high-volume work.

https://t.co/OoM83SyISN

[joe sai @_blue_sweater_]

@CSGO500 Is this true? @grok

[Falcons Esports @FalconsEsport]

Niko finally getting his first major 🥹

#IEM

[joe sai @_blue_sweater_]

提前下班

[joe sai @_blue_sweater_]

@xmanplez @thsottiaux ok

[joe sai @_blue_sweater_]

第一版还在早期测试阶段。

如果你也是 Mac 用户，经常从文章、视频、AI 对话里保存内容，欢迎试用：
https://t.co/dX6vqVpSYf

[joe sai @_blue_sweater_]

我做了一个 Mac 小工具，叫 Kiko。

因为我自己经常遇到一个问题：

视频太长，没时间完整看；
文章和 AI 对话里看到有用的东西，
又懒得专门打开笔记软件整理。

所以我做了 Kiko。

选中文字，或者粘贴视频链接，
它会帮你整理成一张本地知识卡片。

希望以后看到有用的内容时，
可以更轻松地顺手保存下来。

[joe sai @_blue_sweater_]

Codex 快速模式并不是“速度快 1.5 倍，消耗也只多 1.5 倍”。

如果你用的是 GPT-5.5，实际消耗是 2.5 倍 credits。

https://t.co/ieSJ2DN8Lt

[joe sai @_blue_sweater_]

@grok

[joe sai @_blue_sweater_]

有没有那种不靠暴论博眼球，但持续分享高质量 AI 内容的博主？求推荐🤔

[joe sai @_blue_sweater_]

reset 万岁 🫡

[Tibo @thsottiaux]

Some of you noticed limits drained faster in Codex, we root caused it to an optimization that we rolled back that had an impact on cache hit rates when compacting across long running sessions.

We fixed this and have now reset usage limits for all accounts. Enjoy the weekend.