vochicong

👷ML/AI❤️Chess/Shogi 📝Math. Optimization Mastodon: @[email protected]

[vochicong @vochicong]

期待以上と期待外れは紙一重。期待外れの働きができなければ期待以上の働きも難しい。

[Y Combinator @ycombinator]

We’ve decided to open-source a multi-agent harness we use internally at YC.

We call it “QM” and it’s meant to be easy to customize, like Hermes or OpenClaw, but useful for a whole company. We use it across accounting, legal, events, and engineering (including building QM itself!).

The whole project is under an MIT license. It is cloud-first and has Slack and web UI natively.

[vochicong @vochicong]

https://t.co/0GanL9WDHh

[Tabish @0xTab]

This is one of the coolest projects I've seen in recent times; it takes building in public to the next level.

An agent that builds itself autonomously and evolves in real time, all while maintaining a public journal that shows what work the agent decides to take on.

The future of software has never been more exciting.

[vochicong @vochicong]

https://t.co/dHrjgoODp5

[Boris Cherny @bcherny]

I'm Boris and I created Claude Code. I wanted to quickly share a few tips for using Claude Code, sourced directly from the Claude Code team. The way the team uses Claude is different than how I use it. Remember: there is no one right way to use Claude Code -- everyones' setup is different. You should experiment to see what works for you!

[vochicong @vochicong]

https://t.co/ScxGSdCvt6
生成AI集中講義 (5-Day AI Agents Intensive Course with Google) の動画を NotebookLM で作ったら分かりやすかった

[Gemini Notebook @Gemini_Notebook]

Introducing ✨ Featured Notebooks ✨

Starting today, you will see a new section on your homepage of featured notebooks. These will include everything from scientific exploration to practical level guides to expert advice.

Learn more and access the notebooks directly here ⬇️

https://t.co/H1vWCxoxDA

[vochicong @vochicong]

I just bought Mike Rourke @codelikeawolf a coffee on @buymeacoffee for helping me move my data from Toggl to Clockify! 🎉

You can support him here — https://t.co/4pCu2Wsv7c

[vochicong @vochicong]

@NotebookLM Please support interactive quizzes, like in Gemini Canvas!

[vochicong @vochicong]

The original AI: how your brain tracks language patterns https://t.co/lGB9pfhc2f

[LangChain @LangChain]

LangChain Academy is live! Our first course — Introduction to LangGraph — teaches you the in-and-outs of building a reliable AI agent.

In this course, you’ll learn how to:
🛠️ Build agents with LangGraph's graph-based workflows
🔄 Use memory + human-in-the-loop for smarter, self-corrective agents
📚 Create your own AI assistant that can perform knowledge tasks

Enroll now for free ➡️ https://t.co/oGYHCgurxo
Bring LangChain Academy to your company ➡️ https://t.co/3qwFcKNvsY

[vochicong @vochicong]

【#超サイヤ人4ゴジータ参戦 】6周年キャンペーン開催中！合体戦士の超パワーを体感しよう！ #ドラゴンボールレジェンズ6周年 #レジェンズ

[vochicong @vochicong]

ゴジ4かっこよすぎ😍
#超サイヤ人4ゴジータ参戦

[Yann LeCun @ylecun]

Yet another opportunity to point out that reasoning abilities and common sense should not be confused with an ability to store and approximately retrieve many facts.

[Frank Nielsen @FrnkNlsn]

Must-read excellent books with 🆓 PDF available to download from the author/book web pages:

👉 https://t.co/zXELEi8E4W

[Kazunori Sato @kazunori_279]

BigQuery で Vertex AI の LLM を使用して SQL のみで RAG を構築する｜クラウドエース株式会社 https://t.co/dPtYkZcxKQ

[vochicong @vochicong]

AIの安全性よりも性能向上が優先されているのか。

OpenAI、退社したライケ氏のAGI警鐘に応じるも具体策は明示せず https://t.co/JdQ7spGegV

[Yann LeCun @ylecun]

The competitive nature of human societies drives people to do complex things that few other people can do, regardless of the level of abstraction at which they operate, and regardless of what tools they use.
Look at the stack of skills that are required of computer engineers and computer scientists: device physics, circuit design, computer architecture, assembly programming, compilers, system programming, native application programming, software architecture, domain R&D (AI, scientific computing, CAD, whatever), ....
At every level, there is competition, excellence, and specific skills.
Many brilliant AI scientists and engineers only program in Python and only have a vague idea of compilation, assembly, CUDA kernels, OS design, and computer architecture, let alone circuit design and device physics.
That doesn't make them lazy.

[Grant Sanderson @3blue1brown]

The next chapter about transformers is up on YouTube, digging into the attention mechanism: https://t.co/TWNXiWM2az

The model works with vectors representing tokens (think words), and this is the mechanism that allows those vectors to take in meaning from context.

[Omega Crafter (オメガクラフター) @omegacrafter_jp]

オメガクラフターのプログラミングの雰囲気がよくわかる動画です👀どこまで効率化を突き詰めることができるのでしょうか…!?!?
#OmegaCrafter