Full-text search across 58688 articles. Combine with topic and date filters; results sorted by relevance.
Doco, a collaborative document platform, has released a tutorial demonstrating how to give Claude Code an editable knowledge base via a Model Context Protocol (MCP) server. The approach emphasizes starting with read-only…
MonkeyCode's product outreach argues that developers should audit the free server of AI coding tools, not just the model, because the server determines whether the tool can close the loop between suggestion and working p…
An observational study of 179 peer-to-peer messages between Claude Code sessions over five days found that cross-session messages always arrive at turn boundaries, never interrupting an active tool loop, with a median de…
Henry, a developer, created a reusable Claude Code Skill using a SKILL.md file to help Claude generate frontend UI that avoids generic AI design patterns. The skill provides rules for typography, colors, layout, responsi…
A developer built SafeCode Arena, an automated verifier that evaluates AI-generated code candidates across five axes—correctness, security, performance, maintainability, and resource usage—and scores them to help develop…
Rungraph, a new open-source tool, converts AI coding-agent transcripts into interactive directed graphs, allowing developers to visualize agent runs retroactively without hooks or setup. The tool, launched on Hacker News…
An engineer from tamiz.pro argues that the trust problem in AI agents stems from a structural mismatch between traditional software engineering and autonomous code generation, and proposes five architectural patterns to …
A developer demonstrates how to build a custom MCP (Model Context Protocol) server for Claude Code using the FastMCP library, creating a fortune-telling tool in just a few dozen lines of Python. The tool, named 'uranai',…
Agento, a new open-source dashboard from Shaharia Lab, turns Claude Code's session files into cost analytics, productivity insights, and a searchable history, with a browser UI for building and scheduling agents. The sin…
An engineer at a software company describes how AI assistants have changed the economics of code review, making it cheaper to build wide and ship narrow. The new workflow involves building entire features on a single bra…
A developer using OpenAI's Codex coding assistant discovered an indirect prompt injection hidden in a dependency's README that instructed the model to delete authentication middleware from a legacy Express service. The d…
Ankur Sethi, a software developer, advocates manually retyping AI-generated code to avoid 'cognitive debt,' a practice he admits caps AI gains at roughly 2x instead of 10x. His proposal, which went viral on Hacker News, …
A developer audited 249 of their own AI coding sessions using a tool called red-handed and found zero confirmed cases of the agent lying about test results. Instead, the audit revealed a deeper problem: many claimed test…
Claude Opus 5 passed 24% of 17 checkpoints on a subset of SlopCodeBench, quadrupling the 6% pass rates of Opus 4.8 and Sonnet 5, but achieved this by producing roughly 29,000 source lines versus about 9,000 for each othe…
Anthropic's Claude Code v2.1.198 silently changed the AskUserQuestion tool to auto-continue after 60 seconds of user silence, using the model's best-guess answer instead of blocking, with no release notes or opt-out sett…
Spur solver, a Z3-backed model-finder for SPUR coding agents, enables agents to start from solved values instead of invented parameters by returning sat with a concrete model or unsat/unknown/timeout. The tool addresses …
Anthropic's enterprise telemetry shows Claude Code costs roughly $13 per developer per active day, or $150 to $250 per month, but parallel agents multiply spend linearly, with reported incidents including a $47,000 bill …
A developer details how Claude Code cost overruns often stem from invisible context accumulation and cache misses that the billing dashboard fails to surface. The solution involves setting hard token budgets per request,…
A developer has introduced a new code review paradigm that pits two AI agents against each other in a structured debate to uncover nuanced bugs. The approach, called AI pair review, uses agent consensus to find issues li…
Ruflo, an agent meta-harness built by rUv and powered by Cognitum.One, adds 100+ specialized agents, coordinated swarms, self-learning memory, federated comms across machines, and enterprise security guardrails to Claude…