Full-text search across 59753 articles. Combine with topic and date filters; results sorted by relevance.
A developer found that fixing a subtle bug in a Rust program manually was easier than prompting an agentic AI tool like OpenCode or Pi, noting that the prompt required would be as long as a blog post. The fix simplified …
A developer measured the token cost of their Claude Code configuration and found that 107 skills, 38 agents, and 15 commands consume 9,857 tokens in every session before any input is typed. The developer created a script…
Camille Roux released genart-skill, a plugin for Anthropic's Claude Code that teaches the AI assistant the working knowledge of generative art, including deterministic hash-seeded PRNGs, resolution-independent rendering,…
A new informal tier list from Brokk, based on coding performance in Rust static analysis tooling, ranks OpenAI's Luna subscription as the top value, solving more than 10x as many DeepSWE tasks per $200 than any competito…
Coding agents often fail because they lack structured validation, but dmx, an MCP server, introduces 'gated loops' that force agents to pass specific checks before proceeding, shifting from probabilistic execution to det…
A study by the coding agent company Droid found that single-agent runs stop early on long-horizon software tasks because they validate work locally without a complete standard of completion. In a test rebuilding GDAL fro…
A developer has open-sourced Foremerge, a coordination protocol that helps parallel coding agents avoid semantic conflicts that Git cannot detect. The tool allows agents to declare their intents before acting, and it det…
A developer has spent six months running a one-person film studio using Anthropic's Claude Code, producing a 10-episode series. The setup relies on a CLAUDE.md file that defines Claude's role as a creative director, SKIL…
A developer estimates that human code review costs $0.243 per changed line, 2.1 times the $0.114 model spend for an AI agent to produce an accepted changed line, based on a SmartBear/Cisco study, U.S. Bureau of Labor Sta…
Alibaba released the model weights for Qwen3.8-Flash-Next, a multimodal mixture-of-experts model with 125B parameters plus 51B N-gram embeddings and 6B activated per token, as a preview of the Qwen4 architecture. NVIDIA …
Ivan Li, a technical lead and frontend engineer specializing in AI-powered video products, advocates for a stabilization phase before writing more code in software rescues. He emphasizes defining a concrete release path,…
A developer has detailed a setup that provides free access to frontier AI models like GPT Sol and Claude Opus using two open-source tools: OmniRoute, a local API gateway, and Pi, a coding agent. The configuration routes …
Anthropic has signed the European Union's Code of Practice on Transparency of AI-Generated Content and is implementing machine-readable watermarking across all output from its Claude models worldwide, starting August 2. …
AWS Lambda raised its per-account code storage limit from 75GB to 300GB per Region and introduced a new REFERENCE mode that lets functions point directly to S3 objects, bypassing the quota entirely, effective July 15. Th…
A developer at MonkeyCode, an open-source project offering free model access, reported that a coding agent produced a 2,000-line diff for a task that should have required only 40 lines, despite passing tests. The root ca…
A developer has created IPL (Intent Programming Language), a minimalist DSL designed to enforce deterministic code generation with LLMs by constraining the expression space. The language uses a reduced grammar and separa…
A developer discovered that MCP servers were silently consuming up to 111,000 tokens per conversation in Claude Code, wasting an estimated $2,500 per year. By auditing and removing unused servers, they reduced context ov…
A developer with no coding background describes how, over four months, they built a live business with an AI partner by enforcing accountability through a custom harness. The developer's key rule was that the AI could no…
Developer Randal Schwartz has open-sourced dart-sdk-skills, a version-by-version skill package that equips AI coding agents with complete knowledge of Dart features from 1.0 to 3.14, addressing the training cutoff frustr…
A developer integrated Claude Code agents as first-pass reviewers in the pull request process for a multinational iOS team, saving about 30 minutes per engineer per day. The multi-agent system fans out over diffs with na…