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. ActionKit by Paragon - Connect to 130+ SaaS integrations (e.g. Slack, Salesforce, Gmail) with Paragon’s ActionKit API. Adfin - The only platform you need to get paid - all payments in one place, in
January 30, 2023 In this post, we'll implement a GPT from scratch in just 60 lines of numpy. We'll then load the trained GPT-2 model weights released by OpenAI into our implementation and generate some text. Note: This post assumes familiarity with Python, NumPy, and some basic experience with neural networks. This implementation is for educational purposes, so it's missing lots of features/improv
PyTorch and TensorFlow are far and away the two most popular Deep Learning frameworks today. The debate over which framework is superior is a longstanding point of contentious debate, with each camp having its share of fervent supporters. Both PyTorch and TensorFlow have developed so quickly over their relatively short lifetimes that the debate landscape is ever-evolving. Outdated or incomplete in
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
型安全かつシンプルなAgentフレームワーク「PydanticAI」の実装を解剖する - ABEJA Tech Blog
はじめに こちらはABEJAアドベントカレンダー2024 12日目の記事です。 こんにちは、ABEJAでデータサイエンティストをしている坂元です。最近はLLMでアプローチしようとしていたことがよくよく検証してみるとLLMでは難しいことが分かり急遽CVのあらゆるモデルとレガシーな画像処理をこれでもかというくらい詰め込んだパイプラインを実装することになった案件を経験して、LLMでは難しそうなことをLLM以外のアプローチでこなせるだけの引き出しとスキルはDSとしてやはり身に付けておくべきだなと思うなどしています（LLMにやらせようとしていることは大抵難しいことなので切り替えはそこそこ大変）。 とはいうものの、Agentの普及によってより複雑かつ高度な推論も出来るようになってきています。弊社の社内外のプロジェクト状況を見ていても最近では単純なRAG案件は減りつつあり、計画からアクションの実行、結果
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
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
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
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
Prompt Engineering
Date: March 15, 2023 | Estimated Reading Time: 21 min | Author: Lilian Weng Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation a
Parsing SQL - Strumenta
The code for this tutorial is on GitHub: parsing-sql SQL is a language to handle data in a relational database. If you worked with data you have probably worked with SQL. In this article we will talk about parsing SQL. It is in the same league of HTML: maybe you never learned it formally but you kind of know how to use it. That is great because if you know SQL, you know how to handle data. However
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
Join a VS Code Dev Days event near you to learn about AI-assisted development in VS Code. Update 1.54.1: The update addresses an issue with an extension dependency. Update 1.54.2: The update addresses these issues. Update 1.54.3: The update addresses this issue. Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Welcome to the February 2021 release of Vi
はじめての自然言語処理 Fusion-In-Decoder でクイズに答えるモデルを作る | オブジェクトの広場
今回は Fusion-In-Decoder を使ってクイズに答えるモデルを作ります。以前から Wikipedia 等の外部情報を参照できるテキスト生成モデルを試してみたいと思っていました。Fusion-In-Decoder の発表は 2020 年なので少し前のモデルですが、T5 ベースで手軽に試せるサイズ感ですので、日本語で試してみましょう。 1. はじめに 今回紹介する Fusion-In-Decoder（以下、FiD ）1 は Meta AI (当時は Facebook AI Research) が発表した Open Domain question Answering タスクを解くテキスト生成モデルです。 じつは、以前から外部情報を参照できるテキスト生成モデルを試してみたくて2、 Google の RETRO3 の論文を読んでたんです。 なのですが、外部情報のサイズ感が 1000 B
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
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. A year and a half ago, during Google Cloud Next 24, we published this list for the first time. It numbered 101 entries. It felt like a lot at the time, and served as a showcase of how much momentum b
It is December. That means annoying Christmas things are everywhere, including but not limited to the annual programming semi-competition known as Advent of Code. The problem with Advent of Code is that it is a waste of time. Most of the puzzles are in the realm of either string processing (somewhat applicable to programming), logic puzzles (not really applicable to most programming), or stupid go
Lean for JavaScript DevelopersSeptember 2, 2025 This is my opinionated syntax primer for the Lean programming language. It is far from complete and may contain inaccuracies (I’m still learning Lean myself) but this is how I wish I was introduced to it, and what I wish was clarified. Why Lean? This post assumes you’re already eager to learn a bit of Lean. For motivation, I humbly submit to you two
How a simple Linux kernel memory corruption bug can lead to complete system compromise
In this case, reallocating the object as one of those three types didn't seem to me like a nice way forward (although it should be possible to exploit this somehow with some effort, e.g. by using count.counter to corrupt the buf field of seq_file). Also, some systems might be using the slab_nomerge kernel command line flag, which disables this merging behavior. Another approach that I didn't look
Date: June 23, 2023 | Estimated Reading Time: 31 min | Author: Lilian Weng Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerfu
VSeeFace
Contents About Download Terms of use Credits VSFAvatar Tutorials Manual FAQ Virtual camera Transparency Network tracking Special blendshapes Expressions VMC protocol Model posing iPhone tracking Perception Neuron ThreeDPoseTracker Troubleshooting Preview in Unity Translations Running on Linux Troubleshooting Startup Tracking/Webcam Virtual camera Model issues Lipsync Game capture Log folder Perfor
This paper reflects work done in late 2022 and 2023 to audit for vulnerabilities in terminal emulators, with a focus on open source software. The results of this work were 10 CVEs against terminal emulators that could result in Remote Code Execution (RCE), in addition various other bugs and hardening opportunities were found. The exact context and severity of these vulnerabilities varied, but some
Tips on Adding JSON Output to Your CLI App - Brazil's Blog
Brazil's Blog Musings on automation, scripting, programing, DevOps, and cybersecurity A couple of years ago I wrote a somewhat controversial article on the topic of Bringing the Unix Philosophy to the 21st Century by adding a JSON output option to CLI tools. This allows easier parsing in scripts by using JSON parsing tools like jq, jello, jp, etc. without arcane awk, sed, cut, tr, reverse, etc. in
Update 1.85.1: The update addresses these issues. Update 1.85.2: The update addresses these issues. Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Welcome to the November 2023 release of Visual Studio Code. There are many updates in this version that we hope you'll like, some of the key highlights include: Floating editor windows - Drag and drop edit
How is AI changing the way we work? Our previous research on AI’s economic impacts looked at the labor market as a whole, covering a variety of different jobs. But what if we studied some of the earliest adopters of AI technology in more detail—namely, us? Turning the lens inward, in August 2025 we surveyed 132 Anthropic engineers and researchers, conducted 53 in-depth qualitative interviews, and
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
Bucket full of secrets – Terraform exfiltration | Mercari Engineering
Background At Mercari, we utilize many microservices developed across multiple different teams. Each team has ownership over not only their code, but also the infrastructure necessary to run their services. To allow developers to take ownership of their infrastructure we use HashiCorp Terraform to define the infrastructure as code. Developers can use Terraform native resources or custom modules pr
I recently shipped Context, a native macOS app for debugging MCP servers. The goal was to build a useful developer tool that feels at home on the platform, powered by Apple's SwiftUI framework. I've been building software for the Mac since 2008, but this time was different: Context was almost 100% built by Claude Code1. There is still skill and iteration involved in helping Claude build software,
I’m a fairly frequent Hacker News lurker, especially when I have some other important task that I’m avoiding. I normally head to the Active page (lots of comments, good for procrastination) and pick a nice long discussion thread to browse. So over time I’ve ended up with a good sense of what topics come up a lot. “The Bay Area is too expensive.” “There are too many JavaScript frameworks.” “Bootcam
昨日は休もうと思ったのにentropixが衝撃的すぎて結局ずっとコンソールに齧り付いていた。今日は技研スタジオの電気工事があるのだが、技研専属電気技師のふかみんがなかなか他のフロアの作業が終わらないので、その間に誘惑に勝てず、再びentropixを触ってみた。 entropixのオリジナルのコードは1B用なので、これを8Bに拡大してみる。 細かい修正点が多かったのでソースコードをフォークして自分のリポジトリに上げた。プルリクするにはちょっとかけ離れた内容になってしまったので。 8Bにするにあたり、トークナイザーとモデルはLlama3.1をベースにした。 8Bは元々だいぶ賢いのだが、それでも「9.11と9.9はどちらが大きい?」と聞くと、自信満々に「9.11」と返してくるので厄介なモデルである。まあClaude-3もそうだけどね。 1Bでも360Mでも間違わなかったこの質問、entropix
From my perspective, one of the biggest open problems in implementing programming languages is how to add a type system to the language without significantly complicating the implementation. For example, in my tutorial Fall-from-Grace implementation the type checker logic accounts for over half of the code. In the following lines of code report I’ve highlighted the modules responsible for type-che
GIMP 2.99.12 is a huge milestone towards GIMP 3.0. Many of the missing pieces are getting together, even though it is still a work in progress. As usual, issues are expected and in particular in this release which got important updates in major areas, such as canvas interaction code, scripts, but also theming… “CMYK space invasion”, by Jehan (based on GPLv3 code screencast), Creative Commons by-sa
PySkyWiFi: completely free, unbelievably stupid wi-fi on long-haul flights | Robert Heaton
The plane reached 10,000ft. I took out my laptop, planning to peruse the internet and maybe do a little work if I got really desperate. I connected to the in-flight wi-fi and opened my browser. The network login page demanded credit card details. I fumbled for my card, which I eventually discovered had hidden itself inside my passport. As I searched I noticed that the login page was encouraging me
I did this in 2020 and then again in 2021, but I’m in the mood to look around again. Let’s look through Are We GUI Yet? and see what’s up these days. The task today is to have a text label and an input field that can change the text in the label. In React, for example, this is basically free: const Demo = () => { let [state, setState] = useState("Hello, world!"); return ( <div> <p>{state}</p> <inp
Introduction Some part of me has always been fascinated with coercing code to run in weird places. I scratch this itch a lot with my security research projects. These often lead me to writing shellcode to run in kernels or embedded hardware, sometimes with the only way being through an existing bug. For those not familiar, shellcode is honestly hard to describe. I don’t know if there’s a very form
Reading the excellent article by JeanHeyd Meneide on how broken string encoding in C/C++ is made me realise that Unicode is a topic that is often overlooked by a large number of developers. In my experience, there’s a lot of confusion and wrong expectations on what Unicode is, and what best practices to follow when dealing with strings that may contain characters outside of the ASCII range. This a
I spend an awful lot of my day in Unix terminals running shell commands. For some reason, the variance in efficiency between different people when using the shell is huge: I know people who can run rings around me, and I’ve come across more than one paid professional who doesn’t use the “up” key to retrieve the previous command. I chose that last example very deliberately: most of the commands mos
20 December 2022 I present to you: The GB Interceptor. It is an adapter that goes between an unmodified Game Boy and the cartridge and offers a video stream of the game via USB. Click the image to see the video on youtube.com. The video above should give you a good overview of what it does, how it works and what its limitations are. This article here goes more into the technical details of how it
I’m excited to announce the project I’ve been working on for the last year and a half: Game Bub, an open-source FPGA based retro emulation handheld, with support for Game Boy, Game Boy Color, and Game Boy Advance games. Play Video: Game Bub can play physical cartridges, as well as emulated cartridges using ROM files loaded from a microSD card. Game Bub also supports the Game Link Cable in both GB
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
GPT in 60 Lines of NumPy | Jay Mody
PyTorch vs TensorFlow in 2023
Writing a C compiler in 500 lines of Python
Changing std::sort at Google’s Scale and Beyond
RFC 9562: Universally Unique IDentifiers (UUIDs)
Kalyn: a self-hosting compiler for x86-64
February 2021 (version 1.54)
0.8.0 Release Notes ⚡ The Zig Programming Language
Advent of Code on the Nintendo DS
Lean for JavaScript Developers — overreacted
LLM Powered Autonomous Agents
"�[31m"?! ANSI Terminal security in 2023 and finding 10 CVEs
November 2023 (version 1.85)
How AI Is Transforming Work at Anthropic
0.10.0 Release Notes ⚡ The Zig Programming Language
I Shipped a macOS App Built Entirely by Claude Code
Hacker News folk wisdom on visual programming
驚異のLLMテクノロジーentropixを8Bに拡張するとどうなったか?｜shi3z
Unification-free ("keyword") type checking
GIMP - Development version: GIMP 2.99.12 Released
A 2025 Survey of Rust GUI Libraries
Rust on MIPS64 Windows NT 4.0
Unicode is harder than you think · mcilloni's blog
Laurence Tratt: Better Shell History Search
There oughta be a Game Boy capture cartridge.
Game Bub: open-source FPGA retro emulation handheld