CodeQL is the static analysis engine behind GitHub code scanning, which finds and remediates security issues in your code. We’ve recently released CodeQL 2.25.3, which adds support for Swift 6.3,… The
| Date | Count |
|---|---|
| 2026-05-06 | 34 |
| 2026-05-07 | 48 |
| 2026-05-08 | 26 |
| 2026-05-09 | 14 |
| 2026-05-10 | 36 |
| 2026-05-11 | 288 |
| 2026-05-12 | 56 |
AI要約 はじめに OpenAI Codex と Claude Code を両方使っていると、単純な「どちらが賢いか」とは別に、かなり現実的な差が見えてきます。 それが コスト感 です。 ここでいうコストは、月額料金だけではありません。 どれくらい作
og AI要約 本題: VScodeで初歩的なカウントアプリを作って学習中に、次の問題に直面した。 Live Serveer機能でHTMLを記述したファイルを表示しようとしても表示されなくなってしまった。 ※最初の投稿かつ備忘録としての書きなぐりためいろい
![[備忘録-1] VScode内でHTMLをGo Liveしようとしたがうまくいかなかった。](https://qiita-user-contents.imgix.net/https%3A%2F%2Fqiita-user-contents.imgix.net%2Fhttps%253A%252F%252Fcdn.qiita.com%252Fassets%252Fpublic%252Farticle-ogp-background-afbab5eb44e0b055cce1258705637a91.png%3Fixlib%3Drb-4.1.1%26w%3D1200%26blend64%3DaHR0cHM6Ly9xaWl0YS11c2VyLXByb2ZpbGUtaW1hZ2VzLmltZ2l4Lm5ldC9odHRwcyUzQSUyRiUyRmF2YXRhcnMuZ2l0aHVidXNlcmNvbnRlbnQuY29tJTJGdSUyRjI2NDIxNzkwMCUzRnYlM0Q0P2l4bGliPXJiLTQuMS4xJmFyPTElM0ExJmZpdD1jcm9wJm1hc2s9ZWxsaXBzZSZiZz1GRkZGRkYmZm09cG5nMzImcz03YTE1OTJkMWU4MzlmNTM5MzI3NTY1NTkzZDk3MTY1ZA%26blend-x%3D120%26blend-y%3D467%26blend-w%3D82%26blend-h%3D82%26blend-mode%3Dnormal%26s%3D93ed1f865eb8f8d4528ed3975b3ac179?ixlib=rb-4.1.1&w=1200&fm=jpg&mark64=aHR0cHM6Ly9xaWl0YS11c2VyLWNvbnRlbnRzLmltZ2l4Lm5ldC9-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&mark-x=120&mark-y=112&blend64=aHR0cHM6Ly9xaWl0YS11c2VyLWNvbnRlbnRzLmltZ2l4Lm5ldC9-dGV4dD9peGxpYj1yYi00LjEuMSZ3PTgzOCZoPTU4JnR4dD0lNDBhbHN6ZXJvMzIyJnR4dC1jb2xvcj0lMjMxRTIxMjEmdHh0LWZvbnQ9SGlyYWdpbm8lMjBTYW5zJTIwVzYmdHh0LXNpemU9MzYmdHh0LXBhZD0wJnM9ODU2ZDUwMjI1ZWFmOWE1NzZlMmI5NzkxNmM1ODc5NjI&blend-x=242&blend-y=480&blend-w=838&blend-h=46&blend-fit=crop&blend-crop=left%2Cbottom&blend-mode=normal&s=4d5b3f857ce05205165b39fa2e2b9ba6)
og EN arXiv:2605.08112v1 Announce Type: new Abstract: AI coding agents powered by large language models can read codebases and produce functional code, but they routinely violate team-specific product decis
EN arXiv:2605.08112v1 Announce Type: new Abstract: AI coding agents powered by large language models can read codebases and produce functional code, but they routinely violate team-specific product decis
og EN arXiv:2605.08261v1 Announce Type: new Abstract: Evaluating Computer Use Agents (CUAs) on interactive environments is fraught with methodological pitfalls that the field has yet to systematically addre
EN arXiv:2605.08261v1 Announce Type: new Abstract: Evaluating Computer Use Agents (CUAs) on interactive environments is fraught with methodological pitfalls that the field has yet to systematically addre
og EN arXiv:2605.08267v1 Announce Type: new Abstract: Enterprise AI backends increasingly admit heterogeneous execution requests across model deployment, inference, evaluation, data movement, and agentic wo
EN arXiv:2605.08267v1 Announce Type: new Abstract: Enterprise AI backends increasingly admit heterogeneous execution requests across model deployment, inference, evaluation, data movement, and agentic wo
og EN arXiv:2605.08299v1 Announce Type: new Abstract: Embedding-based code retrieval often suffers when encoders overfit to surface syntax. Prior work mitigates this by using LLMs to rephrase queries and co
EN arXiv:2605.08299v1 Announce Type: new Abstract: Embedding-based code retrieval often suffers when encoders overfit to surface syntax. Prior work mitigates this by using LLMs to rephrase queries and co
EN arXiv:2605.08319v1 Announce Type: new Abstract: Mazocarta is a seeded procedural tactical deckbuilder implemented in Rust, compiled to WebAssembly for browser play, and executable natively for simulat
EN arXiv:2605.08319v1 Announce Type: new Abstract: Mazocarta is a seeded procedural tactical deckbuilder implemented in Rust, compiled to WebAssembly for browser play, and executable natively for simulat
EN arXiv:2605.08380v1 Announce Type: new Abstract: AI agents are increasingly framed as software-engineering teammates, yet most research studies them inside human-centered workflows. Little is known abo
EN arXiv:2605.08380v1 Announce Type: new Abstract: AI agents are increasingly framed as software-engineering teammates, yet most research studies them inside human-centered workflows. Little is known abo
EN arXiv:2605.08435v1 Announce Type: new Abstract: Agentic AI coding tools such as Claude Code and OpenAI Codex execute multi-step coding tasks with limited human oversight. To steer these tools, develop
EN arXiv:2605.08435v1 Announce Type: new Abstract: Agentic AI coding tools such as Claude Code and OpenAI Codex execute multi-step coding tasks with limited human oversight. To steer these tools, develop
EN arXiv:2605.08553v1 Announce Type: new Abstract: Large language models can generate useful code from natural language, but their outputs come without correctness guarantees. Verifiable code generation
EN arXiv:2605.08553v1 Announce Type: new Abstract: Large language models can generate useful code from natural language, but their outputs come without correctness guarantees. Verifiable code generation
EN arXiv:2605.08621v1 Announce Type: new Abstract: Frequent toolchain updates and growing ISA diversity have made system-level software package repair increasingly important. Diagnosing and repairing bui
EN arXiv:2605.08621v1 Announce Type: new Abstract: Frequent toolchain updates and growing ISA diversity have made system-level software package repair increasingly important. Diagnosing and repairing bui
EN arXiv:2605.08680v1 Announce Type: new Abstract: LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix t
EN arXiv:2605.08680v1 Announce Type: new Abstract: LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix t
EN arXiv:2605.08694v1 Announce Type: new Abstract: Automated theorem proving is essential for the formal verification of safety-critical systems. As the corpus of formal proofs grows, a natural paradigm
EN arXiv:2605.08694v1 Announce Type: new Abstract: Automated theorem proving is essential for the formal verification of safety-critical systems. As the corpus of formal proofs grows, a natural paradigm
EN arXiv:2605.08717v1 Announce Type: new Abstract: Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad ho
EN arXiv:2605.08717v1 Announce Type: new Abstract: Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad ho
EN arXiv:2605.09023v1 Announce Type: new Abstract: LLMs show strong performance in code generation, but their outputs lack correctness guarantees. Sample-based uncertainty estimators address this by gene
EN arXiv:2605.09023v1 Announce Type: new Abstract: LLMs show strong performance in code generation, but their outputs lack correctness guarantees. Sample-based uncertainty estimators address this by gene
EN arXiv:2605.09051v1 Announce Type: new Abstract: The Solidity smart contract ecosystem has rapidly grown, leading to multiple compilers targeting different blockchain platforms or improving compilation
EN arXiv:2605.09051v1 Announce Type: new Abstract: The Solidity smart contract ecosystem has rapidly grown, leading to multiple compilers targeting different blockchain platforms or improving compilation
EN arXiv:2605.09059v1 Announce Type: new Abstract: Code generation is one of the tasks for which the use of Large Language Models is widely adopted and highly successful. Given this popularity, there are
EN arXiv:2605.09059v1 Announce Type: new Abstract: Code generation is one of the tasks for which the use of Large Language Models is widely adopted and highly successful. Given this popularity, there are
EN arXiv:2605.09304v1 Announce Type: new Abstract: Many software development tasks, such as implementing features and fixing bugs, begin with developers posing questions about a codebase. However, answer
EN arXiv:2605.09304v1 Announce Type: new Abstract: Many software development tasks, such as implementing features and fixing bugs, begin with developers posing questions about a codebase. However, answer
EN arXiv:2605.09393v1 Announce Type: new Abstract: Context: Large Language Models (LLMs) are increasingly influencing software engineering practice and education. While prior studies examine their techni
EN arXiv:2605.09393v1 Announce Type: new Abstract: Context: Large Language Models (LLMs) are increasingly influencing software engineering practice and education. While prior studies examine their techni
EN arXiv:2605.09421v1 Announce Type: new Abstract: Code authorship attribution (CAA) supports software forensics, plagiarism detection, and intellectual property protection. However, existing supervised
EN arXiv:2605.09421v1 Announce Type: new Abstract: Code authorship attribution (CAA) supports software forensics, plagiarism detection, and intellectual property protection. However, existing supervised
EN arXiv:2605.09573v1 Announce Type: new Abstract: Concurrency testing is essential to improve the reliability and security of multi-threaded programs. Dynamic analysis tools, such as TSan, depend on hig
EN arXiv:2605.09573v1 Announce Type: new Abstract: Concurrency testing is essential to improve the reliability and security of multi-threaded programs. Dynamic analysis tools, such as TSan, depend on hig
EN arXiv:2605.09658v1 Announce Type: new Abstract: Traditional Search-Based Software Engineering (SBSE) assumes global search and full Pareto exploration are essential. We offer the following negative re
EN arXiv:2605.09658v1 Announce Type: new Abstract: Traditional Search-Based Software Engineering (SBSE) assumes global search and full Pareto exploration are essential. We offer the following negative re
EN arXiv:2605.09734v1 Announce Type: new Abstract: Most language-model training data shows final artifacts, not the process that produced them. We study a tractable version of this question in tool use:
EN arXiv:2605.09734v1 Announce Type: new Abstract: Most language-model training data shows final artifacts, not the process that produced them. We study a tractable version of this question in tool use:
EN arXiv:2605.09817v1 Announce Type: new Abstract: Agent tools are becoming a core interface through which LLM agents access external data, services, and execution environments. As these tools are distri
EN arXiv:2605.09817v1 Announce Type: new Abstract: Agent tools are becoming a core interface through which LLM agents access external data, services, and execution environments. As these tools are distri
EN arXiv:2605.09894v1 Announce Type: new Abstract: Modernizing legacy COBOL systems remains difficult due to scarce expertise, large and long-lived codebases, and strict correctness requirements. Recent
EN arXiv:2605.09894v1 Announce Type: new Abstract: Modernizing legacy COBOL systems remains difficult due to scarce expertise, large and long-lived codebases, and strict correctness requirements. Recent
EN arXiv:2605.10039v1 Announce Type: new Abstract: Frontier coding agents read configuration files (CLAUDE.md, AGENTS.md, Cursor Rules) at session start and are expected to follow the conventions inside
EN arXiv:2605.10039v1 Announce Type: new Abstract: Frontier coding agents read configuration files (CLAUDE.md, AGENTS.md, Cursor Rules) at session start and are expected to follow the conventions inside
EN arXiv:2605.10240v1 Announce Type: new Abstract: Software vulnerability detection is critical for ensuring software security and reliability. Despite recent advances in deep learning, real-world vulner
EN arXiv:2605.10240v1 Announce Type: new Abstract: Software vulnerability detection is critical for ensuring software security and reliability. Despite recent advances in deep learning, real-world vulner
EN arXiv:2605.10382v1 Announce Type: new Abstract: Design Research Methodology (DRM) supports systematic design research through representations such as Reference Models and Impact Models. However, the p
EN arXiv:2605.10382v1 Announce Type: new Abstract: Design Research Methodology (DRM) supports systematic design research through representations such as Reference Models and Impact Models. However, the p
EN arXiv:2605.10408v1 Announce Type: new Abstract: Testing robots requires assessing whether they perform their intended tasks correctly, dependably, and with high quality, a challenge known as the test
EN arXiv:2605.10408v1 Announce Type: new Abstract: Testing robots requires assessing whether they perform their intended tasks correctly, dependably, and with high quality, a challenge known as the test
EN arXiv:2605.10597v1 Announce Type: new Abstract: Benchmarks for coding agents increasingly measure source-level software repair, and cybersecurity benchmarks increasingly measure broad capture-the-flag
EN arXiv:2605.10597v1 Announce Type: new Abstract: Benchmarks for coding agents increasingly measure source-level software repair, and cybersecurity benchmarks increasingly measure broad capture-the-flag