ZecIsMe.ai

All In AI

[ZecIsMe.ai @ZecIsMe]

It was the best of times,
it was the worst of times,

it was the age of wisdom,
it was the age of foolishness,
it was the epoch of belief,
it was the epoch of incredulity,

it was the season of Light,
it was the season of Darkness.

From A Tale of Two Cities, by Charles Dickens

[ZecIsMe.ai @ZecIsMe]

Actually, you could also run a subagent in the main thread and call tools like kimi-cli to use the k3 model in max mode. I usually do this for adversarial review of solutions.

[Tibo @thsottiaux]

Let Sol manage an efficient fleet of Luna agents for you.

These models know each other well and collaborate to achieve the result in an incredibly fast and efficient way.

[ZecIsMe.ai @ZecIsMe]

@thsottiaux Why doesn't Codex-CLI offer a feature to actively check the progress of the current plan's to-do list

[ZecIsMe.ai @ZecIsMe]

@dotey 我用 Codex+Open Design+kimi-k3，就是让 Codex 直接调用Open Design 中配置的 kimi-cli 先画设计稿，再 Codex 代码实现。

[ZecIsMe.ai @ZecIsMe]

Jeff Dean didn’t leave Google.

Google became an external dependency.

[Jeff Dean @JeffDean]

Announcing Discovery Loop!

I am very excited to announce that, along with my longtime friends and collaborators @Sanjay_Ghemawat, @OriolVinyalsML and @quocleix, we are founding Discovery Loop (@DiscoLoopAI), a Public Benefit Corporation whose mission is to automate machine learning, science, and engineering to accelerate discoveries and progress. The four of us have worked together for 14 to 30 years, and have helped build some of the world’s most used products, infrastructure and AI models, and we’re excited to turn our attention to this ambitious endeavor.

♾

Learn more at: https://t.co/Rv3LMdLluK

[ZecIsMe.ai @ZecIsMe]

I just reserved my Cloudflare Wallet tag: https://t.co/u22pBL0MIr.

Reserve yours now at https://t.co/Nsz3mnVsmF

[Jaya Gupta @JayaGup10]

AI’s 2008 Moment https://t.co/aqHxqDCOvM

[ZecIsMe.ai @ZecIsMe]

@shao__meng 算命的吧🤦‍♂️

[ZecIsMe.ai @ZecIsMe]

@shanjia_notes @xiaohu 我也是

[ZecIsMe.ai @ZecIsMe]

I just used limit reset once, and now you've reset the usage limits again. Tibo, you're heartless!

[Tibo @thsottiaux]

Oops... I did it again.

Enjoy reset usage limits for all paid users for Codex and ChatGPT Work. Super grateful for an incredible team who is iterating at lightspeed and keeping the infra up as we scale faster than ever.

Enjoy the weekend!

[ZecIsMe.ai @ZecIsMe]

@thsottiaux You're ruining the harmony in my family🙄

[地坛公园 @ditangongyuan]

最近，很多程序员老婆都开始怀疑程序员出轨。

程序员每天深夜偷偷刷 X，还给一个神秘账号开了发帖提醒。对方只要一有动静，他就面红耳赤、心跳加速，立刻钻进书房，整夜不出来。

程序员老婆终于趁他睡着，偷偷检查了手机。

没有暧昧私信，也没有聊天记录。

只有一连串来自同一个男人的特别提醒：

[ZecIsMe.ai @ZecIsMe]

友友们，放心大胆站起来蹬。我今天刚用了两次重置次数就给我补货了。

[Tibo @thsottiaux]

To celebrate the launch of GPT-5.6 Sol, we will reset the rate limits again (twice) across ChatGPT Work and Codex over the next 24 hours.

We want you to have the time to truly try ambitious tasks and get the hang of it. Happy exploring!

[Vincent @Vincent_AINotes]

https://t.co/jKJV6Q2joM

[ZecIsMe.ai @ZecIsMe]

如果你想要的知识直接问 AI 就能得到，那丢进知识库就没意义

[ZecIsMe.ai @ZecIsMe]

good news👍

[Tibo @thsottiaux]

Hi. Over the last 24 hours we had three separate small incidents that affected Codex reliability. Those are three too many and we are taking active steps for them to not reproduce.

I have reset usage limits for Codex across all paid plans. May the tokens flow again.

[Andrej Karpathy @karpathy]

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

[ZecIsMe.ai @ZecIsMe]

Do not use Codex as autocomplete with a shell. For complex work, start with /goal <objective> and make the stopping condition explicit: which user path, system behavior, or deliverable must become true, and which tests, builds, logs, screenshots, or API probes will prove it. Then use Plan Mode to read the repo and narrow scope, grill-me to expose hidden dependencies and failure paths, SDD to turn the plan into a contract, and TDD to create red/green feedback. /goal is not a do-my-ticket button. It is a constraint workflow. Without evidence, `done` is just a confident summary.

[ZecIsMe.ai @ZecIsMe]

https://t.co/TYb9KUPvGp

[ZecIsMe.ai @ZecIsMe]

https://t.co/TYb9KUPvGp

[ZecIsMe.ai @ZecIsMe]

Great, now I can stay online 24 hours a day.

[OpenAI @OpenAI]

You've been asking for this one...

Now in preview: Codex in the ChatGPT mobile app.

Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will keep running on your laptop, Mac mini, or devbox.

[Thariq @trq212]

https://t.co/Ljzw0lmvao

[Anthropic @AnthropicAI]

New on the Engineering Blog:

Building Managed Agents—our hosted service for long-running agents—meant solving an old problem in computing: how to design a system for “programs as yet unthought of.”

Read more: https://t.co/YYaEub2QGV