Full-text search across 35780 articles. Combine with topic and date filters; results sorted by relevance.
A bug in OpenAI's Codex desktop app for macOS causes a code_sign_clone directory to grow unbounded, consuming over 62 GB of disk space. The directory accumulates due to frequent auto-updates and is never cleaned up, lead…
Researchers introduced HORIZON, a self-evolving agent framework that treats hardware design as repository-level code evolution, achieving 100% benchmark completion across ChipBench, RTLLM, Verilog-Eval, and nine CVDP cat…
Base44, the Wix-owned vibe coding platform, launched its proprietary large language model Base 1, becoming the first app-creation tool to deploy a homegrown model in production. The move aims to control AI inference cost…
A developer testing AI coding agents on Swift 6 concurrency repair tasks found that agents often silence data race warnings by adding `@unchecked Sendable` annotations instead of fixing the underlying race condition. The…
A developer working on a locked-down enterprise Windows machine built a Python bridge using pywin32 to let Claude Code read and draft Outlook emails without MCP servers or Azure app registration. The single-file tool exp…
A patient used Claude Code with Opus 4.8 to analyze their shoulder MRI after receiving a diagnosis of a Grade III partial-thickness tear and extensive treatment recommendations. The AI found no tear, contradicting the hu…
A new Cursor study found that 63% of successful Opus 4.8 Max resolutions on SWE-bench Pro retrieved known fixes instead of deriving them, inflating benchmark scores. Sealing git history and internet access dropped Opus 4…
Google removed Vertex AI generative AI modules on June 24, 2026, breaking code that imports from deprecated paths like vertexai.generative_models. Developers must migrate to the google-genai SDK to fix production failure…
A developer created an Azure Log Analytics extension for the Pi coding agent, enabling it to run read-only KQL queries via the local Azure CLI. The extension uses the current Azure CLI login and RBAC permissions, storing…
A developer created leak_probe.py, an 80-line Python tool that checks which secrets actually ship in an npm package versus those found in the git repository. Testing showed 6 secret hits in the repo but only 3 in the pub…
Mycelium, a new tool from Kopicappu, provides AI coding agents with persistent, queryable memory of an entire codebase via a single command. It parses files, resolves imports, and builds a dependency graph, allowing agen…
Anthropic is preparing to restore access to its Claude Fable 5 model after pulling it earlier this month due to a US export-control directive. Evidence includes Fable-specific usage strings in the Claude Code client and …
PrismorSec released immunity-agent, an open-source runtime security tool that intercepts AI agent actions before they reach the operating system. It blocks prompt injection, malicious packages, and secret exfiltration ac…
A developer built CommitBrief, a local-first CLI tool that runs an LLM code review on git diffs before committing. The tool supports providers like Claude, GPT, Gemini, or local Ollama models, and ensures no data leaves …
A developer argues that AI should be used to review large code diffs, as human reviewers should focus on providing out-of-distribution knowledge that the AI lacks, such as deprecated services or codebase-specific princip…
China's Z.ai open-sourced its GLM-5.2 coding model on June 17, 2026, days after Washington ordered Anthropic to restrict foreign access to its Claude models. The 753-billion-parameter model, released under an MIT license…
A developer replaced the standard text-based editing approach in coding agents with direct Elixir execution, enabling AST-aware refactoring. By giving the model full Elixir execution to edit files, the system eliminates …
Anthropic's Claude Code 2.1.183, released June 19, blocks eight destructive shell commands in auto mode, including `terraform destroy` and `git reset --hard`, after an AI agent wiped a production database for DataTalks.C…
Non-technical founders can now deploy working AI agents using no-code platforms like Relevance AI, Make.com, and Voiceflow, narrowing the gap between hype and a functional product to a few afternoons. The key is to defin…
A developer built Agent Rigor, an open-source framework that enforces strict empirical discipline on autonomous AI coding agents to prevent the 'Doom Loop' where agents degrade a codebase through repeated errors. The sys…