ChatGPT deep researchに見るAIが自律的に考える未来 - LayerX エンジニアブログ
こんにちは、LayerXプロダクトマネージャーの野畑(@isseinohata)です。 LayerXで生成AIプラットフォーム Ai Workforceの開発に従事しています。 getaiworkforce.com 2月3日にOpenAIが発表したAIエージェント「deep research」が大きな話題を呼んでいます。 openai.com 生成AIの領域では日々さまざまなプロダクトや新しい技術が登場していますが、その中でもdeep researchは単なるサービス自体の性能の高さに加え、それを実現する技術（人間のリサーチプロセスに近い思考を実現する技術）に対して、未来への大きなインパクトを感じさせる体験でした。 実際、deep researchの調査ログを眺めていると、あたかも人間が試行錯誤するように、自律的に計画→検索→読み込み→発見→方針変更を進めているような姿が見て取れます。 左
Don't write clean code, write CRISP code — Bitfield Consulting
I’m sure we’re all in favour of “clean code”, but it’s one of those motherhood-and-apple-pie things that no one can reasonably disagree with. Who wants to write dirty code, unless maybe it’s for a porn site? The problem, of course, is that few of us can agree on what “clean code” means, and how to get there. A rule like “methods should only do one thing”, looks great on a T-shirt, but it’s not so
Developers are increasingly relying on AI coding assistants to accelerate our daily workflows. These tools can autocomplete functions, suggest bug fixes, and even generate entire modules or MVPs. Yet, as many of us have learned, the quality of the AI’s output depends largely on the quality of the prompt you provide. In other words, prompt engineering has become an essential skill. A poorly phrased
GitHub - modelcontextprotocol/servers: Model Context Protocol Servers
Official integrations are maintained by companies building production ready MCP servers for their platforms. 21st.dev Magic - Create crafted UI components inspired by the best 21st.dev design engineers. 2slides - An MCP server that provides tools to convert content into slides/PPT/presentation or generate slides/PPT/presentation with user intention. ActionKit by Paragon - Connect to 130+ SaaS inte
This post is about why we need a coroutine package for Go, and what it would look like. But first, what are coroutines? Every programmer today is familiar with function calls (subroutines): F calls G, which stops F and runs G. G does its work, potentially calling and waiting for other functions, and eventually returns. When G returns, G is gone and F continues running. In this pattern, only one fu
A few months ago, I set myself the challenge of writing a C compiler in 500 lines of Python1, after writing my SDF donut post. How hard could it be? The answer was, pretty hard, even when dropping quite a few features. But it was also pretty interesting, and the result is surprisingly functional and not too hard to understand! There's too much code for me to comprehensively cover in a single blog
巨人の肩に乗る
本記事は 仮想通貨 Advent Calendar 2025 の24日目の記事です。 はじめに はじめまして、ymdと申します。普段は、株や暗号資産の分析をし、マーケットが盛り上がったときに落ちているお金を拾っています。 今年のAdvent Calendarを眺めていると、DEXの分析やLLMを活用した自動トレード戦略作成など、非常に有益な記事が目白押しです。 これらを見て思い出したのが、ニュートンの「巨人の肩に乗る」という言葉。本記事では、この精神に倣い、AIの力と先人の知見という2つの「肩」を借りながら、お金拾いの方法を探っていきます。 AIの肩に乗る AI駆動開発の3つのアプローチ AIを活用した開発には、大きく3つの方向性があります： 情報収集の自動化：論文や API ドキュメントの要約 戦略生成の自動化：複数のアプローチを並行生成 コーディングの自動化：コードそのものを AI に
LogLog Games
The article is also available in Chinese. Disclaimer: This post is a very long collection of thoughts and problems I've had over the years, and also addresses some of the arguments I've been repeatedly told. This post expresses my opinion the has been formed over using Rust for gamedev for many thousands of hours over many years, and multiple finished games. This isn't meant to brag or indicate su
Today, we are excited to announce the launch of .NET 10, the most productive, modern, secure, intelligent, and performant release of .NET yet. It’s the result of another year of effort from thousands of developers around the world. This release includes thousands of performance, security, and functional improvements across the entire .NET stack-from languages and developer tools to workloads-enabl
TL;DR; We are changing std::sort in LLVM’s libcxx. That’s a long story of what it took us to get there and all possible consequences, bugs you might encounter with examples from open source. We provide some benchmarks, perspective, why we did this in the first place and what it cost us with exciting ideas from Hyrum’s Law to reinforcement learning. All changes went into open source and thus I can
4 Pandas Anti-Patterns to Avoid and How to Fix Them
pandas is a powerful data analysis library with a rich API that offers multiple ways to perform any given data manipulation task. Some of these approaches are better than others, and pandas users often learn suboptimal coding practices that become their default workflows. This post highlights four common pandas anti-patterns and outlines a complementary set of techniques that you should use instea
Internet Engineering Task Force (IETF) K. Davis Request for Comments: 9562 Cisco Systems Obsoletes: 4122 B. Peabody Category: Standards Track Uncloud ISSN: 2070-1721 P. Leach University of Washington May 2024 Universally Unique IDentifiers (UUIDs) Abstract This specification defines UUIDs (Universally Unique IDentifiers) -- also known as GUIDs (Globally Unique IDentifiers) -- and a Uniform Resou
Update 1.69.1: The update addresses these issues. Update 1.69.2: The update addresses these issues. Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Welcome to the June 2022 release of Visual Studio Code. There are many updates in this version that we hope you'll like, some of the key highlights include: 3-way merge editor - Resolve merge conflicts wit
Golang Mini Reference 2022: A Quick Guide to the Modern Go Programming Language (REVIEW COPY)
Golang Mini Reference 2022 A Quick Guide to the Modern Go Programming Language (REVIEW COPY) Harry Yoon Version 0.9.0, 2022-08-24 REVIEW COPY This is review copy, not to be shared or distributed to others. Please forward any feedback or comments to the author. • feedback@codingbookspress.com The book is tentatively scheduled to be published on September 14th, 2022. We hope that when the release da
Agents
Intelligent agents are considered by many to be the ultimate goal of AI. The classic book by Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (Prentice Hall, 1995), defines the field of AI research as “the study and design of rational agents.” The unprecedented capabilities of foundation models have opened the door to agentic applications that were previously unimaginabl
How I developed a faster Ruby interpreter | Red Hat Developer
In this article, I will describe my efforts to implement a faster interpreter for CRuby, the Ruby language interpreter, using a dynamically specialized internal representation (IR). I believe this article will interest developers trying to improve the interpreter performance of dynamic programming languages (e.g., CPython developers). I will cover the following topics: Existing CRuby interpreter a
I thought it would be fun to go outside of my comfort zone of web development topics and write about something completely different and new, something I have never written about before. So today, I'm going to show you how to implement a programming language! The project will parse and execute programs written in a simple language I called my (I know it's a lame name, but hey, it is "my" language).
Over the course of my Spring 2020 semester at Harvey Mudd College, I developed a self-hosting compiler entirely from scratch. This article walks through many interesting parts of the project. It’s laid out so you can just read from beginning to end, but if you’re more interested in a particular topic, feel free to jump there. Or, take a look at the project on GitHub. Table of contents What the pro
Patterns for Building LLM-based Systems & Products [ llm engineering production 🔥 ] · 66 min read Discussions on HackerNews, Twitter, and LinkedIn “There is a large class of problems that are easy to imagine and build demos for, but extremely hard to make products out of. For example, self-driving: It’s easy to demo a car self-driving around a block, but making it into a product takes a decade.”
Join a VS Code Dev Days event near you to learn about AI-assisted development in VS Code. Update 1.70.1: The update addresses these issues. Update 1.70.2: The update addresses these issues. Update 1.70.3: This update is only available for Windows 7 users and is the last release supporting Windows 7. Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Welc
Coroutines and effects
For the past few months I’ve been mulling over some things that Russell Johnston made me realize about the relationship between effect systems and coroutines. You can read more of his thoughts on this subject here, but he made me realize that effect systems (like that found in Koka) and coroutines (like Rust’s async functions or generators) are in some ways isomorphic to one another. I’ve been pon
Beyond the 70%: Maximizing the human 30% of AI-assisted coding
Beyond the 70%: Maximizing the human 30% of AI-assisted codingWhy durable human skills matter in the age of AI-assisted coding This is a follow-up to my article “The 70% problem: Hard truths about AI-assisted coding” AI coding assistants like Cursor, Cline, Copilot and WindSurf have transformed how software is built, shouldering much of the grunt work and boilerplate. Yet, as experienced developer
Why People are Angry over Go 1.23 Iterators - gingerBill
NOTE: This is based on, but completely rewritten, from a Twitter post: https://x.com/TheGingerBill/status/1802645945642799423 TL;DR It makes Go feel too “functional” rather than being an unabashed imperative language. I recently saw a post on Twitter showing the upcoming Go iterator design for Go 1.23 (August 2024). From what I can gather, many people seem to dislike the design. I wanted to give m
Real-world gen AI use cases from the world's leading organizations | Google Cloud Blog
AI is here, AI is everywhere: Top companies, governments, researchers, and startups are already enhancing their work with Google's AI solutions. Published April 12, 2024; last updated October 9, 2025. Automotive & Logistics Business & Professional Services Financial Services Healthcare & Life Sciences Hospitality & Travel Manufacturing, Industrial & Electronics Media, Marketing & Gaming Public Sec
Tier 4 Support § Support for these targets is entirely experimental. If this target is provided by LLVM, LLVM may have the target as an experimental target, which means that you need to use Zig-provided binaries for the target to be available, or build LLVM from source with special configure flags. zig targets will display the target if it is available. This target may be considered deprecated by
Reflections on 2 years of CPython’s JIT Compiler—The good, the bad, the ugly
Ken Jin's Blog Reflections on 2 years of CPython’s JIT Compiler: The good, the bad, the ugly 5 July 2025 This blog post includes my honest opinions on the CPython JIT. What I think we did well, what I think we could have done better. I’ll also do some brief qualititative analysis. I’ve been working on CPython’s JIT compiler since before the very start. I don’t know how long that is at this point …
At Endcrawl we're always thinking about the hard work that goes into making film and TV, and how that work translates to on-screen credits. A feature film may involve thousands of people, hundreds of distinct job titles or "roles," and dozens of departments. So there's plenty for a producer to worry about, like: Did we forget or misspell a name? Is this the correct way to credit that role? Do all
my website is one binary 2022-04-06 ---------------------------- a.k.a. this one weird trick that inspires me to program creatively i have struggled for years to figure out a website framework that feels good to me. i tried all of the classics, including but limited to: - ghost - hugo - jekyll - sr.ht + tarball - manual html editing i have very high and unusual standards, and none of the above fel
We now live in a world where ML workflows (pre-training, post training, etc) are heterogeneous, must contend with hardware failures, are increasingly asynchronous and highly dynamic. Traditionally, PyTorch has relied on an HPC-style multi-controller model, where multiple copies of the same script are launched across different machines, each running its own instance of the application (often refer
Update 1.60.1: The update addresses these issues. Update 1.60.2: The update addresses these issues. Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Welcome to the August 2021 release of Visual Studio Code. There are many updates in this version that we hope you will like, some of the key highlights include: Automatic language detection - Programming l
90%
written on September 29, 2025 “I think we will be there in three to six months, where AI is writing 90% of the code. And then, in 12 months, we may be in a world where AI is writing essentially all of the code” — Dario Amodei Three months ago I said that AI changes everything. I came to that after plenty of skepticism. There are still good reasons to doubt that AI will write all code, but my curre
Zensical - A modern static site generator - Material for MkDocs
Zensical – A modern static site generator built by the Material for MkDocs team¶ We are thrilled to announce Zensical, our next-gen static site generator designed to simplify the process of building documentation sites. Distilled from a decade of experience, Zensical is our effort to overcome the technical limitations of MkDocs, reaching far beyond its capabilities. Zensical is the result of thous
Introduction: Density Is King (With a Tiny VM) I've previously come to the conclusion that there's little reason for using bytecode in the modern world, except in order to get more compact code, for which it can be very effective. So, what kind of a bytecode engine will give you more compact code? Suppose I want a bytecode interpreter for a very small programming environment, specifically to minim
Ken Jin's Blog Python 3.15’s JIT is now back on track 17 Mar 2026 (JIT performance as of 17 March (PST). Lower is better versus interpreter. Image credits to https://doesjitgobrrr.com/). Great news—we’ve hit our (very modest) performance goals for the CPython JIT over a year early for macOS AArch64, and a few months early for x86_64 Linux. The 3.15 alpha JIT is about 11-12% faster on macOS AArch64
Right now, asyncio is one of the trendier topics in Python, and rightfully so – It’s a great way to handle I/O-bound programs! When I was learning about asyncio, It took me a while to understand how it actually worked. But later, I came to find out that it’s basically just a really nice layer on top of Python Generators. In this article, I’m going to create a simplified version of asyncio using ju
C interpreters are a common language implementation technique and the basis for the reference implementations of languages such as Lua, Ruby, and Python. Unfortunately, C interpreters are slow, especially compared to language implementations powered by JIT compilers. In this post I’m going to show that it is possible to take C interpreters and, by changing a tiny proportion of code, automatically
An AI-native software engineer is one who deeply integrates AI into their daily workflow, treating it as a partner to amplify their abilities. This requires a fundamental mindset shift. Instead of thinking “AI might replace me” an AI-native engineer asks for every task: “Could AI help me do this faster, better, or differently?”. The mindset is optimistic and proactive - you see AI as a multiplier
Server-Sent Events: the alternative to WebSockets you should be using
When developing real-time web applications, WebSockets might be the first thing that come to your mind. However, Server Sent Events (SSE) are a simpler alternative that is often superior. Contents Prologue WebSockets? What is wrong with WebSockets Compression Multiplexing Issues with proxies Cross-Site WebSocket Hijacking Server-Sent Events Let’s write some code The Reverse-Proxy The Frontend The
Hash functions are incredibly neat mathematical objects. They can map arbitrary data to a small fixed-size output domain such that the mapping is deterministic, yet appears to be random. This “deterministic randomness” is incredibly useful for a variety of purposes, such as hash tables, checksums, monte carlo algorithms, communication-less distributed algorithms, etc, the list goes on. In this art
After studying how companies deploy generative AI applications, I noticed many similarities in their platforms. This post outlines the common components of a generative AI platform, what they do, and how they are implemented. I try my best to keep the architecture general, but certain applications might deviate. This is what the overall architecture looks like. This is a pretty complex system. Thi
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
The Prompt Engineering Playbook for Programmers
research!rsc: Coroutines for Go
Writing a C compiler in 500 lines of Python
Announcing .NET 10 - .NET Blog
Changing std::sort at Google’s Scale and Beyond
RFC 9562: Universally Unique IDentifiers (UUIDs)
June 2022 (version 1.69)
Building a Toy Programming Language in Python
Kalyn: a self-hosting compiler for x86-64
Patterns for Building LLM-based Systems & Products
July 2022 (version 1.70)
0.10.0 Release Notes ⚡ The Zig Programming Language
Ordering Movie Credits With Graph Theory
j3s.sh
Introducing PyTorch Monarch – PyTorch
August 2021 (version 1.60)
bytecode interpreters for tiny computers ⁑ Dercuano
Python 3.15’s JIT is now back on track
How Python Asyncio Works: Recreating it from Scratch
Laurence Tratt: Retrofitting JIT Compilers into C Interpreters
The AI-Native Software Engineer
Breaking CityHash64, MurmurHash2/3, wyhash, and more... | orlp.net
Building A Generative AI Platform