Full-text search across 61921 articles. Combine with topic and date filters; results sorted by relevance.
Basecamp programmer Stanko built the HEY CLI, its TUI, supporting API, SDK and ActionCable client with Rob over one week using entirely AI-generated "vibe-coded" code that no human reviewed beyond initial project setup, …
David Heinemeier Hansson, creator of Ruby on Rails, had coding agents port 37signals' Campfire chat app to Rust, and repository benchmarks run October 1st show the Rust version serving a room page at 36,120 requests per …
At Supabase Select 2026, Supabase announced that its platform now works code first, letting coding agents set up, change, and check projects through schema and config stored in code. The release includes Declarative Sche…
A 12-year-old developer has released KODA Web v25, a browser-based AI coding mentor running on a Cloudflare Worker, adding native OCR and file ingestion so it can read screenshots and uploaded source files directly. The …
Veracode's 2026 GenAI Code Security Report, covering code from more than 100 models, found AI-generated code compiled almost every time but passed security checks only about half the time when tested without security-spe…
A developer built dry-mcp, an MCP server that detects duplicated code by semantic similarity rather than token matching, ranking findings by maintenance cost and delivering results to AI agents instead of a dashboard. Th…
A developer essay argues that AI coding agents should be allowed to propose policy changes but never approve them, because an agent that can rewrite the rules it is checked against makes verification meaningless. The aut…
Xiaomi released MiMo-V2.6-Flash-RL, a sparse Mixture-of-Experts omnimodal model with 309 billion total parameters and 15 billion active per token, positioned as the efficiency-focused sibling to MiMo-V2.6-Pro-RL with a 1…
A study of credential leakage in third-party AI agent skills found 520 affected skills containing 1,708 issues, of which 437 were classified as vulnerable and 83 as malicious, according to Wake Forest University assistan…
A developer has revised their codex-workflows and claude-code-workflows agent review processes to add an outcome-based check that forces coding agents to justify proposed work against the user's actual requirements befor…
Security researchers at Accomplish AI found two sandbox escapes in OpenAI's Codex coding agent, including one called Heapjack that achieves unsandboxed remote code execution on a developer's machine from Codex's strictes…
A developer behind the AI system Contenox describes repeatedly attempting to shut down the project, only to revive it, and argues that AI-generated code creates bugs that conventional code review cannot catch. The engine…
GPT-6 Astra reverse engineered the custom challenge-code format of the country guessing game Guessterra purely from example tokens, without access to source code, according to a first-person account by the developer's br…
A developer's analysis draws a parallel between the agentic loop used by coding agents like Claude Code and OpenAI's Codex and the 1978 split of the original TCP protocol into TCP and IP. The piece traces how Vint Cerf, …
Laravel has released Laravel Vet in beta, a Composer plugin that audits PHP dependencies by showing the code each `composer update` would write into `vendor/` and recording trusted packages in a `vet.json` file. Vet hand…
Abloh launched a pull request tool that runs mutation testing on AI-written code to catch bugs before production, positioning itself alongside the code review tool Greptile. The company says its CLI runs locally on a use…
A developer audited Meanwhile, a sponsored status-line tool for Claude Code, Copilot CLI, and VS Code, and found the VS Code extension had been silently broken for its core use case since launch. Two stacked bugs — a 30-…
AI practitioners are advising developers to build model-agnostic agent skills — reusable instruction files, context documents, and plugins — so accumulated prompt and workflow expertise survives switching between harness…
OpenAI reported that by mid-August 2026, its research organization was using 3.1 agent-workdays of runtime for every human workday, with coding agents expanding beyond research and infrastructure code into technical help…
A developer proposes a characterization-testing approach for refactoring untested 'glue' code that writes files, reads environment variables, or changes directories. The method records a frozen ledger of process behavior…