Install
Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
Why a PR walkthrough can pass validation and still be hard to read
1+ hour, 45+ min ago (770+ words) I made an HTML guide for reading pull requests. When I shared it with coworkers, the visual feedback was encouraging, but I still felt that parts were hard to follow. One person wanted to see the explanation before the code…...
Why do Cursor and Claude Code both say connected to my memory server and still share nothing?
1+ hour, 20+ min ago (399+ words) Sharing memory across editors over MCP is a simple mechanism, and the trouble lives in the setup step around it. I checked six persistent memory systems, including the one I work on, for one thing: not whether they claim cross-IDE…...
12% of our posts had an image. The fix: a commit gate, a sha256, and one directory
4+ hour, 35+ min ago (392+ words) On 2026-09-06 we counted the scheduled Bluesky posts our agent had sent over the previous seven days:... Tagged with ai, devtools, programming, productivity....
Obsidian + Claude Code = an AI that remembers your notes · DS TV
16+ hour, 51+ min ago (125+ words) Obsidian + Claude Code = an AI that remembers your notes dutchstartup.ai Obsidian + Claude Code = an AI that remembers your notes Jack Roberts13 September 2026Watch on YouTube - Your AI forgets you between sessions by default, because holding context costs OpenAI and Anthropic money…...
Cutting PR review time is really changing where review happens
6+ hour, 35+ min ago (248+ words) Atlassian reports its Rovo Dev AI reviewer cut PR cycle time by up to 45% internally and 32% for customers (primary source, Jan 2026). That figure gets quoted as proof that AI review saves review time. Read what the reviewer is described as…...
Giving a coding agent more time barely helps
6+ hour, 35+ min ago (627+ words) Real-SWE ran frontier models against licensed, private enterprise codebases (billing, tax, multi-service work) and one number jumped out at me: rollout duration barely moves resolution. 71.4% of rollouts that finished in under 10 minutes FAILED. 73.4% of rollouts that ran 10 minutes or longer…...
Code Dictator vs Wispr Flow vs Claude Code vs Copilot CLI: Free Voice Dictation for AI Coding in VS Code
9+ hour, 56+ min ago (447+ words) Voice input for AI coding assistants got crowded fast in 2026. If you're picking a tool, here's a direct, feature-level comparison — including where the tools we didn't build genuinely win. The honest limitation: it's VS Code-only, and it depends on a…...
Holdout Ledgers Keep Agent Scores Honest
9+ hour, 58+ min ago (1654+ words) A headline agent percentage is not a measurement until the task ledger, metrics, and controls can be re-run by a stranger. Teams that skip that freeze often publish marketing numbers dressed as evaluation, then discover they cannot reproduce the run....
I removed 1,918 comments across twelve workers. 51 of them were load-bearing.
10+ hour, 21+ min ago (606+ words) The project caps comment blocks per file. A census found 2,886 blocks in the repository and 97 files over the cap. The plan was not to delete the text. Every block was relocated verbatim into an evidence ledger, pinned to the blob…...
Claude Code Has an Undocumented Operator That Cancels Deny Rules.
7+ hour, 25+ min ago (799+ words) Version 2.1.269 made a "!" rule apply only inside its own settings source and made a bare "!" a no-op. The "!" prefix appears nowhere in the permissions documentation, and it is the only thing in the system that can carve an exception out…...