Home/Blog/Show HN: I made a guardrail against AI outreach slop (API/MCP)BackendShow HN: I made a guardrail against AI outreach slop (API/MCP)Hacker News Show2026-11-07 21:480 viewsArticle URL: https://maildignity.com/ Comments URL: https://news.ycombinator.com/item?id=50404494 Points: 3 # Comments: 0Source:https://maildignity.com/My favoritesPreviousShow HN: Chrome extension to block sites and increases attention spanNextThe Second Photonic Shock: A ModelRelated postsRedrawing 82 sprites, where the slow step is a person choosingDevelopment covered 28 Sep 2026 to 28 Sep 2026 (commit dates). This window replaced 82 pieces of map art in Myriad Immor0dev.toThe 80.52 Short: why a 65B beating a 501B needed a video to be believedI spent last week trying to explain that parameter count stopped being the whole story. A 65B model I run locally scored0dev.toReview every pull request with Claude Code Action on GitHubYou can have Claude review every pull request and answer @claude mentions in issues without running a server. anthropics0dev.toGoogle’s One-Word SERPs Create a New Rank-Tracking Accuracy ProblemIndependent rank-tracking data identified a significant Google results anomaly in September and October 2026: for some q0dev.to AIAI Brief Companion: Gemini Omni 1.2 Flash, Inkling 2 Small, and Kernel Vulnerability AuditsTL;DR Google rolled out video generation and lower pricing for Gemini Omni 1.2 Flash, while Thinking Machines introduced0dev.to AIMy AI agent said "Forecast for undefined" and no test caught it, so I built a chaos testing toolEvery AI agent demo looks great. The tools answer instantly, the data is clean, and the agent writes a confident, correc0dev.to AI