Full-text search across 58458 articles. Combine with topic and date filters; results sorted by relevance.
System76 Principal Engineer Jeremy Soller announced that the company's COSMIC projects will no longer accept LLM-generated content in code submissions, citing the team's review load and a low acceptance rate for changes …
A developer built an offline, local-first mock DSA interviewer that runs an open-weights LLM entirely on the user's machine, walking candidates through clarifying questions, approach, graduated hints, hidden test runs, c…
AHVM released a client that gives coding agents persistent Linux microVMs with interactive shells, files, networking and snapshots, running on a Linux server the user controls. The tool installs via curl or Homebrew on A…
A developer reconnected Claude Code to an MCP search server over SSE after switching it from stdio, then found that embedding distance scores swing by as much as 54 points for the same target document when a query is mer…
A developer describes building a small in-app server that exposes an installed application's real schemas, live content, and version-matched documentation so coding agents stop inventing plausible but nonexistent functio…
Groundtrack launched a platform that lets coding agents continuously improve by capturing review corrections, failed approaches, and constraints from individual agent sessions across an organization, according to the com…
ArchKeel released version 0.8.3, adding deterministic architecture checks, recursive contracts, and per-rule evidence to its open-source MIT-licensed tooling after a week-long refactor of a large codebase using around 50…
Researchers introduced Code to Control, an approach that synthesizes Python controllers executing directly as policies, separating program structure from parameters so an LLM builds the controller structure while derivat…
Glow Labs researchers found more than 13,000 internal company images published openly on GitHub by developers at over 300 organizations, spread across more than 900 code repositories, after AI coding agents were asked to…
Master's student Hung Tran of the University of Information Technology (VNU-HCM, Vietnam) is seeking an arXiv cs.CV endorsement for his preprint 'The Clipping Trap: A Silent Failure Mode in Overfitted Neural Image Codecs…
Team Syntax and Synergy built Resilix, an autonomous adversarial agent that intentionally breaks code to surface vulnerabilities and auto-generates defensive security patches before code reaches production, as their subm…
PromptPad 0.1.0, a lightweight native editor for writing long coding prompts, was released as a macOS Apple Silicon preview by developer aaravchour. Built with C++20, Qt 6 Widgets, upstream Scintilla and Lexilla, the app…
Darktrace published a demo showing that coding agents including Claude Code, Codex and Kiro-CLI store conversation history on disk without verifying it came from the model, then read that history on startup as trusted co…
TypeSafe has released Perch, a semantic code linting CLI installed via `npm install -g @lakeday/perch`, which scans source files and reports defects such as wrong_order, inverted_condition, off_by_one and unhandled_null …
Discobox launched a tool that runs AI coding agents such as Claude Code, Codex, and OpenCode in disposable sandboxed environments, each with its own clone of a repository, passwordless sudo, nested Docker, a desktop, and…
Iouri Khramtsov argued in a Substack post that falling code quality in AI-assisted development stems from inadequate quality management practices rather than inherent AI limitations. Khramtsov described a layered defensi…
Developers running parallel coding agents are hitting intent conflicts when multiple agents modify the same repository, according to the GitHub projects Foremerge and OpenMsg. Foremerge, which has 19 GitHub stars, explic…
A developer rebuilt their personal portfolio using Claude Code, with the AI writing much of the code while the developer retained control over design, accessibility, SEO, and performance decisions. The production site, b…
A developer's analysis of two viral Hacker News posts argues that AI coding tools have removed the historical cost of building software, which previously forced engineers to discover prior art. The piece cites Bend 2, a …
LittleHorse Enterprises LLC announced version 1.3 of its Saddle Command Center, adding no-code agent deployment, prebuilt task workers, a JavaScript software development kit, and a free serverless trial to its 'Business-…