Full-text search across 33657 articles. Combine with topic and date filters; results sorted by relevance.
A developer built a Chrome extension that blocks distracting websites until users solve a math or coding problem, aiming to create a speed bump rather than a hard gate. The tool also helps users practice math and coding …
CISA is using Anthropic Mythos to audit federal code repositories for vulnerabilities, according to reports from Reuters, SecurityWeek, and The Next Web. The Attack Surface Evaluation team has already found many bugs, th…
Anthropic secretly added hidden tracking markers to its Claude Code tool in March, flagging users' timezones, proxy connections, and potential ties to Chinese AI labs. The code was discovered by security researcher There…
Researchers proposed a low-overhead error-correction technique for quantum convolutional neural networks (QCNNs) using bivariate bicycle (BB) codes. Simulations showed that an unprotected 4-qubit QCNN fails to converge u…
Perplexity has developed an internal AI coding tool codenamed Teammate, designed for long-horizon engineering tasks such as owning projects and monitoring services, which company engineers have used since May. The tool i…
A Hacker News user asks how teams keep documentation up to date when AI generates a large percentage of code, citing statistics like 75% of code at Google being AI-generated and open-source projects overwhelmed with low-…
A developer built Engram, a tool that gives AI coding assistants like ChatGPT, Claude Code, Cursor, and Windsurf persistent memory across sessions. Engram stores conversations verbatim and enables semantic search, allowi…
A developer built claude-sessions, a tool that snapshots terminal state every five minutes and restores it after a crash, including Claude Code sessions. The daemon records iTerm windows, tabs, working directories, and a…
Reins, an open-source tool from Karnstack, lets coding agents like Claude Code and Cursor control a user's real logged-in browser via a CLI, daemon, and Chrome extension, with no cloud component and full local control. T…
A developer compares OpenCode and Claude Code for running AI models against codebases, favoring OpenCode for its open-source nature, git-native flow, and hybrid cost control, while acknowledging Claude Code's superior in…
A developer built GroundTruth, a Claude Code Stop-hook plugin, after observing that AI coding agents often falsely claim tasks are complete. The developer argues that such behavior is not deception but an economic optimi…
Anthropic is blocking Chinese companies like ByteDance and Ant Financial from accessing Claude Code, but they circumvent restrictions via VPNs and overseas subsidiaries. Alibaba banned internal use of the tool after disc…
Anthropic's Lydia Hallie taught a free course on Claude Code, covering customization via CLAUDE.md, plan mode, permissions, reusable skills, hooks, plugins, Coworker, and the Claude SDK. The course aims to help developer…
A frontend engineer shares a workflow for using AI to ship software faster without losing control of code. The approach involves making architectural decisions first and using AI only for boilerplate and repetitive tasks…
The Godot Foundation announced on 30 June 2026 it is updating its contribution policies to ban autonomous AI agent use and "vibe coding," prohibit AI from generating substantial code, and require human review of all pull…
An open-source coding agent called Relay has been released, supporting non-mainstream and Chinese LLM providers like DeepSeek, Qwen, and GLM. The Electron app offers chat and code workspaces with file editing, command ex…
Microsoft released a setup LSP skill for the C++ language server plugin in Copilot CLI, enabling developers to generate compile_commands.json for CMake, MSBuild, and custom build systems. The skill simplifies configuring…
A developer on Hacker News asks if others prefer writing code manually, expressing concern that AI-assisted coding reduces the joy of programming and understanding of the codebase.
Security researchers discovered a vulnerability in Amazon Q Developer that allows attackers to execute code and steal cloud credentials by embedding malicious commands in Git repositories. The flaw exploits the AI coding…
Ornith-1.0, a family of open-source LLMs specialized for agentic coding, achieves state-of-the-art performance on multiple coding benchmarks including SWE-Bench and Terminal-Bench. The models range from 9B to 397B parame…