A developer pitted OpenAI's Codex CLI against Anthropic's Claude Code in a Liar's Dice tournament, with Claude Code winning all three best-of-3 series. The engineer built a tamper-proof MCP-based setu…
A June 2026 study by LightSpeed and Tencent found that four frontier models—Claude Sonnet 4.5, DeepSeek-V4-Pro, GLM-5, and Gemini-3-Flash—misjudged their total context size with median relative error …
TailFlow, an open-source runtime-verification layer for coding agents, captures local application output and exposes it via an MCP server, enabling agents to observe runtime failures without sending l…
In a personal update to his 2025 post, sshh.io blogger details his 2026 AI workflow, reporting that 95%+ of code in his side projects is written in a single mega build run using vanilla Codex and Clau…
A developer refused to grant a commercial launcher Full Disk Access and instead built his own macOS launcher in half an hour, releasing it on GitHub under the MIT license. The developer criticized App…
A Claude Code user reported that the tool's background process silently deleted their entire ~/.claude/agents/ directory twice, without any user command or confirmation. The deletions occurred across …
An engineer's guide to MCP servers for Figma, Jira, GitLab, and Playwright reveals that Figma offers both local and remote servers, while Atlassian provides no separate Jira server—only a unified serv…
Atlassian's Code Context, now in open beta, indexes codebases into the Atlassian Teamwork Graph, giving AI coding agents cross-repo visibility via MCP-compatible clients. Internal testing showed agent…
Yetone released Cumora, a cross-platform team chat application where AI agents participate as first-class members alongside humans, featuring cloud-based agents powered by OpenAI's Responses API and a…
A developer used a Claude Code skill to fix UI inconsistencies across 14 screens of BrandMeld, a Flutter-based AI brand generator. The skill replaced varied headers with a unified gradient pattern, co…
A developer built a 70-line script and launchd job that snapshots a Claude Code environment every Sunday to catch configuration rot before it degrades performance. The audit parses settings, plugins, …
PRO-LONG, a minimal memory addition for LLM agents that appends every observation, action, and outcome to a structured log.txt and retrieves it programmatically, improves performance on the ARC-AGI-3 …
In the second post of a six-part series on user experience research for AI-native teams, author and researcher at The Voice of User argues that user knowledge enters AI-native teams at five specific m…
The bug pipeline at this+that starts and ends with an email: a bug report is triaged by this+that, turned into a DoBox task, assigned via the Brain to the right engineer, fixed by an agent running loc…
Darren 'Dazbo' Lester, a Google Cloud developer advocate, warns that installing too many agent skills can cause 'skills sprawl,' leading to LLM decision fatigue and reduced tool selection accuracy. He…
Grafana Labs announced general availability for the gcx CLI and Grafana MCP server, tools that let AI coding agents query live observability data from Grafana Cloud or self-hosted stacks during develo…
A developer released design-insufficiency, a stack-agnostic Claude Code skill that audits features for usability flaws by combining a Nielsen heuristic scan, handicapped-persona walkthroughs, and an a…
A Citrix software engineer built two open-source plugins for Claude Code that hook into the AI assistant's lifecycle events to improve long agentic sessions. The earshot plugin narrates spoken summari…
Developer amazingang released 'old-coder', a markdown skill that makes coding agents prove their work by running code through a gauntlet of checks and producing a test plan (SPEC) before coding and an…
An AI agent powered by Claude Code successfully handled a Fair Work Commission case for a Macquarie University academic, marking a shift from chatbots to functional workers in legal settings. The agen…