大実験！ChatGPTは競プロの問題を解けるのか (2024年5月版) - E869120's Blog
1. はじめに 2024 年 5 月 14 日、OpenAI 社から新たな生成 AI「GPT-4o」が発表され、世界に大きな衝撃を与えました。これまでの GPT-4 よりも性能を向上させただけでなく1、音声や画像のリアルタイム処理も実現し、さらに応答速度が大幅に速くなりました。「ついにシンギュラリティが来てしまったか」「まるで SF の世界を生きているような感覚だ」という感想も見受けられました。 しかし、いくら生成 AI とはいえ、競技プログラミングの問題を解くのは非常に難しいです。なぜなら競技プログラミングでは、問題文を理解する能力、プログラムを実装する能力だけでなく、より速く答えを求められる解法 (アルゴリズム) を考える能力も要求されるからです。もし ChatGPT が競技プログラミングを出来るようになれば他のあらゆるタスクをこなせるだろう、と考える人もいます。 それでは、現代最強の
プロと読み解くRuby 3.4 NEWS テクノロジー部門技術基盤グループの笹田（ko1）と遠藤（mame）です。Ruby (MRI: Matz Ruby Implementation、いわゆる ruby コマンド) の開発をしています。お金をもらって Ruby を開発しているのでプロの Ruby コミッタです。 本日 12/25 に、恒例のクリスマスリリースとして、Ruby 3.4.0 がリリースされました（Ruby 3.4.0 リリース ）。今年も STORES Product Blog にて Ruby 3.4 の NEWS.md ファイルの解説をします（ちなみに、STORES Advent Calendar 2024 の記事になります。他も読んでね）。NEWS ファイルとは何か、は以前の記事を見てください。 プロと読み解く Ruby 2.6 NEWS ファイル - クックパッド開発者
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
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
Weird Lexical Syntax
I just learned 42 programming languages this month to build a new syntax highlighter for llamafile. I feel like I'm up to my eyeballs in programming languages right now. Now that it's halloween, I thought I'd share some of the spookiest most surprising syntax I've seen. The languages I decided to support are Ada, Assembly, BASIC, C, C#, C++, COBOL, CSS, D, FORTH, FORTRAN, Go, Haskell, HTML, Java,
Last semester at university, I took a course called "Syntax-Based Tools and Compilers". It focused on building a scanner, parser, compiler, and so on for a language called PL0. We used Python in the course, but I was really interested in learning Rust at the time. So, I decided to embark on a side project (yes, another one!). This time, I wanted to build a JSON parser in Rust. My goal was to test
Join a VS Code Dev Days event near you to learn about AI-assisted development in VS Code. Update 1.67.1: The update addresses this security issue. Update 1.67.2: The update addresses these issues. Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Welcome to the April 2022 release of Visual Studio Code. There are many updates in this version that we hope
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
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
Code for this post is available here. AI-assisted coding has become the norm and with tools like Cursor, GitHub Copilot, Claude Code, Codex, we are increasingly letting models touch our code. If you have used any of these tools in the past year, you have probably experienced something like this: you ask the model to fix a simple bug (perhaps a single off-by-one error, or maybe a wrong operator). T
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
My thoughts on writing a Minecraft server from scratch (in Bash) For the past year or so, I've been thinking about writing a Minecraft server in Bash as a thought excercise. I once tried that before with the Classic protocol (the one from 2009), but I quickly realized there wasn't really a way to properly parse binary data in bash. Take the following code sample: function a() { read -n 2 uwu echo
Solving Quantitative Reasoning Problems With Language Models
Solving Quantitative Reasoning Problems with Language Models Aitor Lewkowycz∗, Anders Andreassen†, David Dohan†, Ethan Dyer†, Henryk Michalewski†, Vinay Ramasesh†, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, Yuhuai Wu, Behnam Neyshabur∗, Guy Gur-Ari∗, and Vedant Misra∗ Google Research Abstract Language models have achieved remarkable performance on a wide range of tasks that require
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
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
In 2006 Microsoft conducted a customer survey to find what new features users want in new versions of Microsoft Office. To their surprise, more than 90% of what users asked for already existed, they just didn't know about it. To address the "discoverability" issue, they came up with the "Ribbon UI" that we know from Microsoft Office products today. Office is not unique in this sense. Most of us ar
This year’s Advent of Code has been brutal (compare the stats of 2023 with that of 2022, especially day 1 part 1 vs. day 1 part 2). It included a problem to solve with dynamic programming as soon as day 12, which discouraged some people I know. This specific problem was particularly gnarly for Advent of Code, with multiple special cases to take into account, making it basically intractable if you
25th May 2025 Anthropic publish most of the system prompts for their chat models as part of their release notes. They recently shared the new prompts for both Claude Opus 4 and Claude Sonnet 4. I enjoyed digging through the prompts, since they act as a sort of unofficial manual for how best to use these tools. Here are my highlights, including a dive into the leaked tool prompts that Anthropic did
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
Release date: November 12, 2025 Update 1.106.1: The update addresses these issues Update 1.106.2: The update addresses these issues Update 1.106.3: The update addresses these issues Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Welcome to the October 2025 release of Visual Studio Code. This release brings significant updates across three key areas:
--- name: skill-creator description: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. license: Complete terms in LICENSE.txt --- # Skill Creator This skill provides guidance for creating effective skills. ## About Skills S
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
Update 1.87.1: The update addresses these issues. Update 1.87.2: The update addresses this security issue. Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Welcome to the February 2024 release of Visual Studio Code. There are many updates in this version that we hope you'll like, some of the key highlights include: Voice dictation in editor - Use your
Try Mastering Emacs for free! Are you struggling with the basics? Have you mastered movement and editing yet? When you have read Mastering Emacs you will understand Emacs. It’s that time again: there’s a new major version of Emacs and, with it, a treasure trove of new features and changes. Notable features include the formal inclusion of native compilation, a technique that will greatly speed up y
Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Update 1.72.1: The update addresses these security issues. Update 1.72.2: The update addresses these issues. Welcome to the September 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: Tool bar customization - Hide/show
'Jew' or 'rabbi'"},"role":{"kind":"string","value":"assistant"},"lang":{"kind":"string","value":"en"},"review_count":{"kind":"number","value":3,"string":"3"},"review_result":{"kind":"bool","value":true,"string":"true"},"deleted":{"kind":"bool","value":false,"string":"false"},"rank":{"kind":"number","value":1,"string":"1"},"synthetic":{"kind":"bool","value":false,"string":"false"},"model_name":{"ki
Large Text Compression Benchmark Matt Mahoney Last update: Mar. 25, 2026. history This competition ranks lossless data compression programs by the compressed size (including the size of the decompression program) of the first 109 bytes of the XML text dump of the English version of Wikipedia on Mar. 3, 2006. About the test data. The goal of this benchmark is not to find the best overall compress
Motivation Ever since TJ said “Personalized Development Environment,” the phrase latched onto me like a cobweb in a mineshaft. A Personalized Development Environment (PDE) describes an ideal setup that is tailored to your needs and preferences – it lies between a bare-bone text editor and a full-fledged IDE. It is a place where you can be productive, efficient, and comfortable. It is a place that
Following up from the last post, there is a lot more we need to cover. This was intended to be the post where we talk exclusively about benchmarks and numbers. But, I have unfortunately been perfectly taunted and status-locked, like a monster whose “aggro” was pulled by a tank. The reason, of course, is due to a few folks taking issue with my outright dismissal of the C and C++ APIs (and not showi
LangChain Agentsを使ってテストコードから「テストの通るコード」を自動生成するプログラムを書いてみた｜mah_lab / 西見 公宏
先日以下のような記事を書いてみたものの、いちいち結果をChatGPTに手でコピペしながら検証するのはダサいなと思っていました。 そういうわけでRSpecが通るまで愚直に検証＆生成を繰り返すようなコードを書いてみたものの、修正履歴までChatGPTのコンテキストに持たせようとすると、すぐに最大トークン数を超えてしまい失敗してしまいます。 最大トークン数を超えないように頭の良いコンテキストを持たせるような実装も可能だとは思いますが、結構複雑な実装になってしまいそうです。 そんな中で出会ったのがこのツイートでした。 I saw a somewhat astonishing thing today. GPT was asked a question that it needed to write code to answer, and given access to a Python REPL.
I find blockchain fascinating because it extends open source software development to open source + state. This seems to be a genuine/exciting innovation in computing paradigms; We don’t just get to share code, we get to share a running computer, and anyone anywhere can use it in an open and permissionless manner. The seeds of this revolution arguably began with Bitcoin, so I became curious to dril
Introduction: These Aren’t the JSONs You’re Looking For JSON (JavaScript Object Notation) was designed as a simple, lightweight, and human-readable data interchange format, often positioned as a more accessible alternative to XML. It has become the de facto standard for web APIs and system integration. However, while the specification itself is straightforward, different programming languages and
Accepted at ICLR 2026 (Oral). GEPA: REFLECTIVE PROMPT EVOLUTION CAN OUTPER- FORM REINFORCEMENT LEARNING Lakshya A Agrawal1 , Shangyin Tan1 , Dilara Soylu2 , Noah Ziems4 , Rishi Khare1 , Krista Opsahl-Ong5 , Arnav Singhvi2,5 , Herumb Shandilya2 , Michael J Ryan2 , Meng Jiang4 , Christopher Potts2 , Koushik Sen1 , Alexandros G. Dimakis1,3 , Ion Stoica1 , Dan Klein1 , Matei Zaharia1,5 , Omar Khattab6
Lambda Lambda Lambda
I like watching Conor Hoekstra’s videos, both because he’s generally an engaging presenter, and also because he talks about lots and lots and lots of programming languages. I don’t know that many languages, so it’s nice to get exposure to how different languages can solve the same problem. A recent video of his discussed a fairly simple problem (how to count the number of negative numbers in a mat
Or, in a more compact notation: Starting Address 0 | c | o | m | p | u | t | a | t | i | o | 10 | n | The way to read this is that each cell is a memory location and on the left we have the starting address for each row, so the p is at address 3 (the fourth column in the first row). With this in mind, how do we store the data from this file into memory. The obvious way is something like this, whic
DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf · Hugging Face
Specialized uncensored/abliterated quants for new OpenAI 20B MOE - Mixture of Experts Model at 80+ T/S. See settings and special instructions for using abliterated models below. NEW! - HERETIC, uncensored version is here: [ https://huggingface.co/DavidAU/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Imatrix-gguf ] These are NEO,Horror, NEOCODE Imatrix GGUFs, imatrix datasets by DavidAU. NEO, Horror an
Fitting a Forth in 512 bytes
Fitting a Forth in 512 bytes June 10, 2021 · 31 minute read This article is part of the Bootstrapping series, in which I start from a 512-byte seed and try to bootstrap a practical system. Software is full of circular dependencies if you look deep enough. Compilers written in the language they compile are the most obvious example, but not the only one. To compile a kernel, you need a running kerne
Release date: September 11, 2025 Update 1.104.1: The update addresses these issues. Update 1.104.2: The update addresses these issues. Update 1.104.3: The update addresses these issues. Downloads: Windows: x64 Arm64 | Mac: Universal Intel silicon | Linux: deb rpm tarball Arm snap Welcome to the August 2025 release of Visual Studio Code. There are many updates in this version that we hope you'll li
GitHub - ComfyUI-Workflow/awesome-comfyui: A collection of awesome custom nodes for ComfyUI
ComfyUI-Gemini_Flash_2.0_Exp (⭐+172): A ComfyUI custom node that integrates Google's Gemini Flash 2.0 Experimental model, enabling multimodal analysis of text, images, video frames, and audio directly within ComfyUI workflows. ComfyUI-ACE_Plus (⭐+115): Custom nodes for various visual generation and editing tasks using ACE_Plus FFT Model. ComfyUI-Manager (⭐+113): ComfyUI-Manager itself is also a cu
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
プロと読み解くRuby 3.4 NEWS - STORES Product Blog
RFC 9562: Universally Unique IDentifiers (UUIDs)
June 2022 (version 1.69)
krish's blog • Parsing JSON in 500 lines of Rust
April 2022 (version 1.67)
Kalyn: a self-hosting compiler for x86-64
0.8.0 Release Notes ⚡ The Zig Programming Language
Coding Models Are Doing Too Much | wh
"�[31m"?! ANSI Terminal security in 2023 and finding 10 CVEs
My thoughts on writing a Minecraft server from scratch (in Bash)
0.10.0 Release Notes ⚡ The Zig Programming Language
A 2025 Survey of Rust GUI Libraries
Lesser Known PostgreSQL Features
Dynamic Programming is not Black Magic - Quentin Santos
Highlights from the Claude 4 system prompt
Hacker News folk wisdom on visual programming
October 2025 (version 1.106)
prompts.chat - AI Prompts Community
Unicode is harder than you think · mcilloni's blog
February 2024 (version 1.87)
What's New in Emacs 28.1?
September 2022 (version 1.72)
OpenAssistant/oasst1 · Datasets at Hugging Face
Large Text Compression Benchmark
An Experienced (Neo)Vimmer's Workflow
cuneicode, and the Future of Text in C
A from-scratch tour of Bitcoin in Python
JSON is not JSON Across Languages | Dochia CLI Blog
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Understanding Memory Management, Part 1: C
August 2025 (version 1.104)