Full-text search across 65629 articles. Combine with topic and date filters; results sorted by relevance.
Developer engneer-hamachan released AREA512, an IDE that runs entirely on the M5Stack Cardputer microcontroller, allowing users to write, compile, and run Ruby code on the device. The IDE features a Vim-like editor with …
Stripe's president of technology and business Will Gaybrick said on a16z's podcast that checkout pages will disappear as AI agents handle shopping and payments, with payment shifting from a click-through page to an API e…
CISA added CVE-2025-62593, a critical remote-code-execution flaw in Ray, the distributed AI framework used by OpenAI, Netflix, and Uber, to its Known Exploited Vulnerabilities catalog on August 17, giving federal agencie…
An engineer at MDLC discovered that AI-generated code can silently omit security controls while all automated signals report green. In one build, 'PII encryption at rest' was marked applied in three documents, but a grep…
Junior engineers who learn to use AI tools like GitHub Copilot and Claude Code as disciplined prompt engineers are shipping features in two weeks that previously took a month, according to an unnamed company observer. Th…
A developer released comment-cop.py, a hook that enforces a why-only comment policy for Claude Code and Codex. The script blocks change-history comments, code narration, and comment-heavy changes while ignoring directive…
Chinese AI company Z.ai released GLM 5.3, an open-weight model capable of automating advanced coding and cybersecurity tasks nearly as well as Anthropic's and OpenAI's best models, alongside OpenVuln, a service for scann…
Wiz's autonomous AI agent Red Agent discovered and exploited a GitHub Actions script injection vulnerability in Snowflake's CI/CD pipeline, exfiltrating internal Jira access credentials just five days after the flaw was …
Vercel's AI SDK harness layer now supports Cline, an AI coding agent, through the official adapter @ai-sdk/harness-cline, developed with the Cline team. Cline runs fully in the host process, using the sandbox as a remote…
Cursor, backed by SpaceX, launched Origin, an AI-native code hosting platform now in beta for paid users, designed to handle AI-driven workloads that strain traditional Git infrastructure. Origin supports 22.6 commits pe…
Payward Inc., parent company of cryptocurrency exchange Kraken, has joined Anthropic's Project Glasswing, an invite-only cybersecurity initiative using the Claude Mythos 5 AI model to scan code for vulnerabilities. The p…
A developer argues that asking large language models to plan and implement in one go leads to missed edge cases, and instead recommends a sequential 'grilling' prompt that forces the AI to ask one question at a time, ins…
A developer discovered that a security hook guarding an AI coding agent silently stopped protecting files with non-ASCII paths due to a one-line encoding bug. The hook, which reads JSON from stdin, used the locale encodi…
A new arXiv paper (2608.13607v1) finds that no single signal reliably predicts sample-level regression in large language models after version updates, based on tests across six benchmarks and six model update pairs. The …
Glider, a new terminal tool, lets users drive multiple AI coding CLIs—Claude Code, Cursor Agent, and Antigravity—from one terminal, relaying permission prompts and maintaining project memory. It supports bidirectional ha…
Adlet Balzhanov, a software developer, reports that after testing every AI model with the same coding and writing tasks, only coding improved, while writing outputs remained generic and AI-sounding regardless of model st…
A self-described non-programmer reports that AI-assisted 'vibe coding' served as a gateway into traditional manual programming, despite finding the approach too expensive, opaque, and unsatisfying. The author, who chose …
Z.ai released GLM-5.3, a model with approximately 750B parameters that surpasses Moonshot AI's Kimi K3 on many benchmarks and rivals Claude Fable 5 and GPT-5.6-Sol on some, marking a significant advance in agentic coding…
Simon Willison, creator of Datasette and co-creator of Django, said on Episode 42 of the Talking Postgres podcast that his gold standard for shipping AI-generated code is "Could I explain this to somebody else?" Willison…
Anthropic announced it will add watermarks to all AI outputs from its Claude models, including text, images, code, and files, to comply with the EU AI Act's Article 50(2) Code of Practice. The company is implementing the…