Full-text search across 57083 articles. Combine with topic and date filters; results sorted by relevance.
Thoughtworks technologist Birgitta Böckeler tested running local large language models for agentic coding on Apple M3 Max and M5 Pro machines, finding that while RAM constraints limit model size to 15-25GB for comfortabl…
Codex and Claude Code are competing AI-powered developer tools from OpenAI and Anthropic, respectively, each using state-of-the-art models to read and modify entire codebases. The article compares the two harnesses, noti…
A developer built @ttsc/graph, an MCP tool that provides coding agents with a TypeScript compiler-built code graph instead of raw source files. In benchmarks, it reduces token usage by roughly 10x on structural questions…
An analysis of Claude Code v2.1.143 reveals that the AI coding assistant sends telemetry metrics to Anthropic every five minutes via HTTP POST, with data including API usage, OAuth events, and system attributes. The tele…
A study of 112,382 commits across 28 public repositories found that AI-written code is not more buggy than human-written code, and may be slightly less buggy. The analysis used a provenance detector to classify agent com…
At YoBox, developers use AI coding assistants to accelerate tasks like writing boilerplate, generating tests, and creating documentation, but the technology still requires human judgment for business context, legacy code…
A developer with 12+ years of Magento experience built a RAG-powered code review tool that understands project-specific patterns, not just generic advice. The tool indexes a codebase using tree-sitter for PHP parsing and…
Anthropic released Cowork on Monday, a new AI agent capability that extends the power of its Claude Code tool to non-technical users, allowing the AI to read, edit, and create files in a designated folder on a user's com…
RigMark released a reproducible serving benchmark that measures local AI stacks on agent-shaped code and prose workloads, structured output, cache-busting prefill and concurrent requests rather than a single headline num…
Google's Gemini 4 Argon, run in Google's Antigravity CLI, scored 64 on the Artificial Analysis Coding Agent Index (v1.5), one point ahead of OpenAI's GPT-6.1 Sol (xhigh) running in Codex at 63, according to Artificial An…
Anthropic has hired Addy Osmani, a former Google developer-tools leader who spent about 14 years at Google, to work on Claude Code, as announced on X. Osmani, known for his work on Chrome DevTools, Lighthouse, and Core W…
Anthropic has released Claude Code, a terminal-native coding agent that operates locally and edits files through the command line, sparking debate among developers about its potential to complement or replace IDE-based t…
Developer Greg Herlein released skills-mapper (sm), a Go binary that syncs a user's skill library from git into the per-agent directories used by Claude Code, Copilot, hax, pi, and oh-my-pi, eliminating the need to manua…
Veracode's 2026 GenAI Code Security Report, released July 28, found that AI-generated code passes security checks only 56% of the time across more than 100 models tested over two years, up just one percentage point from …
Slack, a Salesforce-owned company, launched Slack Code, a feature that brings AI coding agents into shared project channels within Slack, enabling teams to collaborate with agents in real time. The feature, described as …
Engineering organizations now pay multiple vendors for AI coding assistants, each billing differently, making it difficult to answer the simple question of monthly cost and value. A new guide outlines practical approache…
An engineer built EdgeGuard, an open-source VS Code extension that uses AI to find security vulnerabilities in code, and discovered that LLMs tend to make optimistic assumptions about unknown functions, leading to false …
A developer argues that AI-assisted development is shipping code with invisible assumptions, and proposes a reliability stack centered on the C4 model to make system boundaries and invariants explicit. The stack includes…
Docker Sandboxes now allow Claude Code and Codex coding agents to run with full autonomy inside isolated microVMs, reducing the risk of granting --dangerously-skip-permissions or --dangerously-bypass-approvals-and-sandbo…
Drift, a semantic version-control layer wrapping Git, turns every commit into an 'Intent' that records the originating prompt, agent model, AST-level mutations, an optional cognitive-state checkpoint, and an Ed25519 sign…