Minibobo

programmer

[Minibobo @minibobo]

你能想象AGI被这样的公司完全掌握吗。

[Guinness Chen @guinnesschen]

If you ever get tired of managing your Codex threads, just let Codex manage itself! Codex can now create threads, search them, organize them, pin the important ones, and spin up worktrees for parallel tasks.

[Deli Chen @victor207755822]

🚀 We’re hiring! DeepSeek is forming a new Harness team to build Code Harness from the ground up—may be you can call it DeepSeek Code or something like this hhh🤣🤣🤣

📍 Based in Beijing. Two roles open:
🧠 Harness Product Manager → https://t.co/oliNbSD8xk
👨‍💻 Harness R&D Engineer → https://t.co/xCSK5wSEAR
Research meets product—let's build it together. Hit the links and apply directly! 🔥
#DeepSeek #CodeHarness #AI #Hiring #ProductManager #Engineering #Beijing #Referral

[Minibobo @minibobo]

gemini 3.5 flash还是不行，和codex差距有点大.

[Tibo @thsottiaux]

We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours.

We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening.

Apologies and now is the time for /fast maxxing.

[Minibobo @minibobo]

I wanted to use up my Kiro quota for this month as soon as possible, so I gave Kiro another chance today, but it was still useless (Tool execution failed). @kirodotdev

[Xuanwo @OnlyXuanwo]

我已经听说至少两个 case，因为阿里内部强推 Qwen，最后让工程师得出了 “Agentic Coding 也不过如此” 的结论了。

马自达太坏了，阿里人天天想着生态闭环该不会也是因为这种水平才想出来的吧？。。

[张小珺 Xiaojun Zhang @zhang_benita]

This episode features an interview with Yao Shunyu @ShunyuYao14 , Research Scientist at Google DeepMind. Yao has held research scientist roles at both Anthropic and Google DeepMind, contributing to the development of key models including Claude 3.7, 4.5, and Gemini 3.

Yao Shunyu is not your typical nerd. Every now and then, he’ll catch you off guard with a flash of irreverence.

“None of the old guard are your relatives — so if you think someone’s being dumb, they’re just being dumb. Say it. No big deal.” (laughs)

“Everyone’s a surfer now, but what really matters is the wave — not the person riding it.”

“AI doesn’t actually require that much brainpower — I mean it genuinely doesn’t — most of this is work any undergrad could do. The most important quality in this industry is reliability: being meticulous, and taking responsibility for what you put out.”

“You don’t need to worry too much about ruffling feathers with your opinions. As long as your views are internally consistent — not just taking random shots at people, but grounded in your own genuine understanding — there are objective standards for how you’re doing in this field. People will respect you for it.”

Let us have a little fun with this one! 😄​​​​​​​​​​​​​​​​

https://t.co/q8AbJKA4Mx

[Minibobo @minibobo]

Kiro is pure garbage. I ran it for a few minutes using Optus 4.6, and then it told me "Invalid model ID. Please select a different model to continue." I couldn't find a refund option either, so I guess I'll just consider the $13 a waste. @kirodotdev

[Jared Roesch @roeschinc]

We open-sourced some amazing work on an experimental Rust compiler for GPU from my colleagues at @nvidia. It takes a slightly different approach to expose GPU programming concepts natively in Rust. Check it out https://t.co/xR4Ho2LUMR.

[Minibobo @minibobo]

It is almost the same as my feeling, and often ootus can give some very good and different designs and suggestions.

[antirez @antirez]

In this place I said many times how strong of a coding agent GPT 5.5 is and how Opus is lagging a bit behind. But, this is part of the story. For the times in our life where we need to seek some advice, Claude Opus versatility and high quality replies are a real gift.

[Minibobo @minibobo]

@yetone 我也遇到过

[Andrew Ng @AndrewYNg]

How we prompt AI is very different in 2026 than 2022 when ChatGPT came out.

I'm teaching a new course, AI Prompting for Everyone, to help you become an AI power user — whatever your current skill level.

It covers skills that apply across ChatGPT, Gemini, Claude, and other AI tools. How to use deep research mode for well-researched reports on complex questions. How to give AI the right context, including more documents and images than most people realize you can provide. When to ask AI to think hard for several minutes on important decisions like what car to buy, what to study, or what job to take. And how to use AI to generate images, analyze data, and build simple games and websites.

I also cover intuitions about how these models work under the hood, so you know when to trust an answer and when not to.

Along the way, you'll see flying squirrels, a creativity test, some of my old family photos, and fireworks.

Join me at https://t.co/tcQc4iJAJG

[图拉鼎 @tualatrix]

早上，我让 Codex 从昨天开始执行的“goal”整整跑了 21 小时 14 分钟，共消耗 9 亿 Token，终于进入了“Goal archived”状态。期间完全没有任何人工干预，它就是不停解决问题、验证结果…不断循环这个过程。

大家可能会好奇我用 Codex 做的什么任务，简单地说，我让它解决的是前后端数据字段的大重构问题。随着产品的不断迭代，早期的一些设计不再适应，需要对数据库建模（model）进行一些重构以适应未来发展。

我的产品后端 PostgreSQL，前端 SwiftData，加上自己实现的同步机制（local-first）。早期 model 还少时，重构会简单的多，现在 model 很多，关系又错综复杂，除非停止迭代，重构如果不一次性完成，任务非常繁杂。但好处是，只要定好标准和方向，重构又是相对容易验收的。

于是我想到了最近 Codex（命令行版本）推出的“/goal”功能（也就是 Codex 版本的“raphl loop”）。通过简单的提示词，指向一份文档让它去实现，就这样它连续跑了 21 小时。

最后验收的效果还不错，除了一些 App 端的小问题（这是我原本就测试没覆盖到的地方，没工作也正常），基本很满意。有了这次经历，我对 Codex（或其他 AI 产品）去解决大重构等长任务越来越有信心了。为了防止 AI 写的代码越来越屎山，也必须需要周期性的去重构、清理架构和代码。

[Minibobo @minibobo]

@9hills 我的claude 已经被封了，不知道有数据用过kiro 不。

[Onur Mutlu @_onurmutlu_]

If you would like study how computers & computing paradigms (e.g., CPU, GPU, NPU/TPU/systolic arrays, SRAM, DRAM) work, lecture videos from Spring 2025 edition of our beginner course, Digital Design & Computer Architecture are all online:

https://t.co/tKmpuxvVIx

@SAFARI_ETH_CMU

[Felipe Coury 🦀 @fcoury]

/goal also lands in Codex CLI 0.128.0.

Our take on the Ralph loop: keep a goal alive across turns. Don't stop until it's achieved.

Built by my co-worker and OpenAI mentor Eric Traut, aka the Pyright guy. One of the GOATs I get to work with daily.

[Minibobo @minibobo]

@OfficialLoganK We need Gemini to provide better coding.

[Minibobo @minibobo]

最近发现 codex 最大的问题就是容易设计过于灵活，从而导致代码复杂度上升几个级别。

[Minibobo @minibobo]

我发现 codex 的 plan 以及设计能力不如 claude，claude 经常能给我一些很好的设计，codex 就不行。