SureDDD

[waishnav @wshxnv]

yesterday, at the Codex hackathon, i ended up solving this problem by building an MCP connector app that turns ChatGPT into Codex, sort of.

1. you get to use GPT-5.5 Pro by exposing your local dev environment to ChatGPT, so you can use 5.5 pro for planning and handover to codex to execute it
2. you get to 2x your rate limits, just like last month, because apparently ChatGPT and Codex have separate rate limits

here is the quick demo

[SureDDD @dengshuo346]

@__tinygrad__ what about data security

[SureDDD @dengshuo346]

@karpathy It’s like using LLMs to search for answers, with each chat session as an iteration.

[Amy Tam @amytam01]

https://t.co/b9f99xbcMx

[SureDDD @dengshuo346]

@dotey 之前一直通过类似的方式让 Coding plan 不再局限于 Coding。。。不过生成代码的形式其实还是在造更个性化的工具，强依赖于模型的输出质量，这么看下来 token 的消耗就更大了

[SureDDD @dengshuo346]

今天ClaudeCode 更新后，通过使用代码的方式来��决问题，这其实也是我一直使用 CodeAgent 来完成非 Coding 人物的手段之一，其实写代码就是造工具，不过这种方式还是非常依赖于模型的生成速率，质量，当然最重要的是成本！

[Meta Open Source @MetaOpenSource]

⚡️OSS Project Spotlight⚡️

Below is a powerful resource monitoring tool for Linux that provides deep insights into system performance, including CPU, memory, I/O, and more — all from an intuitive terminal interface.

Learn more: https://t.co/YVG0NPlzNS

[SureDDD @dengshuo346]

@kkaibiheessssi 去年十一去的火山，挺冷的，草有点黄，山也有点秃了，不过自驾玩玩应该也不错

[Thomas Ratliff @devtom7]

The latest version of Luminar adds support for more streaming sites like HBO Max, which makes for a pretty crazy viewing experience!

#MetaQuest3 #MixedReality #VR #XR #madewithunity

[Georgi Gerganov @ggerganov]

LBDL + llama for scale. thx @francoisfleuret

[Mengxin Liu @liumengxinfly]

这个代码级别的 Ollama 架构解析，讲了不少 Ollama 在代码上的黑科技
https://t.co/qkSfsnoP13

[Bernhard Kerbl @Snosixtytwo]

Happy to announce the results of our latest research, which takes 3D Gaussian Splatting to the next level: "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets," which has been accepted at #SIGGRAPH2024!🎉 Find it here: https://t.co/ZjspxIXPXo

[adammaj @MajmudarAdam]

I've spent the past ~2 weeks building a GPU from scratch with no prior experience. It was way harder than I expected.

Progress tracker in thread (coolest stuff at the end)👇

[SureDDD @dengshuo346]

agree, code is very concise and worth learning

[Cheng @zcbenz]

Having been reading the code of MLX https://t.co/qAW3K70eZ4 for last 2 weeks, it is absolutely the machine learning framework with cleanest code, and it has a nice design.

I recommend it to anyone who want to learn ML from bottom up.

[Meathill @meathill1]

结合前阵子的开发经验，分享一下使用 Vercel Edge Function 访问 OpenAI API 的注意事项，希望新来的开发者少走弯路。 https://t.co/DTRadM10Yn

[SureDDD @dengshuo346]

write by chatgpt?

[Sam Altman @sama]

Planning for AGI and beyond: https://t.co/7PBlNj9KAD

[Casey Muratori @cmuratori]

I have tried this before, and I didn't receive any, but I'd like to try again: can some "Modern C++" advocates out there please send me some examples of real-world code that you think is "well written" by modern C++ standards? Preferably a real project on github or something?

[SureDDD @dengshuo346]

我的杯子应该是过于普通，被同一层有相似杯子的同事拿走了，留下他的杯子在茶水间，已经过去了三天，可他还没发现。

[. @The_ArtOfCode]

How to code a Quadratic Bezier curve in 2 minutes.

[仙壤 @godrealmx]

Thread：为什么说ZK挖矿是下一个值得布局的赛道？

如果你以前并不了解ZK Rollup，同时对“ZK挖矿”这个名词感到耳目一新，那么这条Thread将是值得你阅读并转发的好材料！

1.ZK Rollup中的两大核心角色
主流的ZK Rollup如StarkWare等，其架构包含两大角色：Sequencer（执行交易）
Prover（生成ZK证明）