I genuinely love my Tesla Model Y and what Tesla has built as a product. Which makes my recent service experience even more disappointing. I bought a Certified Used Model Y directly from Tesla Germany. When the car reached me in Bulgaria, several items were missing: - the detachable tow hitch ball - the original Type 2 charging cable - the rear trunk parcel shelf / cargo cover - the Tesla Mobile Connector I reported the missing equipment to Tesla the very next day. Tesla later clarified that the Mobile Connector was not included with the vehicle, and they could not confirm that the parcel shelf should have been included. Fair enough, I’m completely OK with that. But Tesla also confirmed in writing that according to their documentation, my car was supposed to come with the Tow Hitch and the Type 2 charging cable. Then things got strange. - Tesla Greece told me to contact Germany. - Tesla Germany confirmed the missing equipment. - They offered to provide the Type 2 cable and detachable tow ball free of charge. - They arranged for both to be sent to Tesla Thessaloniki. - They even told me when the parts should arrive. - Then the decision was suddenly revoked because another Tesla location refused to cover the cost. All of this over two items that Tesla’s own records say should have been delivered with the car. I still love the car. I genuinely enjoy owning and driving it. But it’s disappointing to see such a great product paired with a service process where different Tesla locations can pass responsibility between each other, and even reverse an already confirmed solution. I hope @Tesla can help get this resolved properly. @elonmusk

Every vibe coder should probably install this GitHub project. If you use Claude Code, Codex, Cursor, Gemini, Copilot, etc. - ctx-wire feels like a no-brainer. The problem is simple: AI coding agents run tons of noisy commands: git, sed, tr, grep, cat, npm, go, cargo, etc. And then they happily dump all that output back into the context window. Result? Your session fills up faster. You burn more tokens. You compact more often. And the agent starts carrying around a lot of useless noise instead of useful context. ctx-wire sits between the agent and the command output. It runs the command, filters/compresses the noisy output, scrubs secrets, and gives the agent a much shorter, cleaner result, while keeping the full scrubbed log locally if something actually fails. Why I like it: - Less token waste - Cleaner agent context - Fewer forced compacts - Better signal-to-noise during long coding sessions - Open source, free, installs in a few lines This is one of those tiny infra/devtools things that feels boring… Until you realize it directly improves the way your AI coding agent thinks. Repo: github.com/pivanov/ctx-wire Install: ctx-wire.dev Cut the noise. Keep the context.

Every vibe coder should probably install this GitHub project. If you use Claude Code, Codex, Cursor, Gemini, Copilot, etc. - ctx-wire feels like a no-brainer. The problem is simple: AI coding agents run tons of noisy commands: git, sed, tr, grep, cat, npm, go, cargo, etc. And then they happily dump all that output back into the context window. Result? Your session fills up faster. You burn more tokens. You compact more often. And the agent starts carrying around a lot of useless noise instead of useful context. ctx-wire sits between the agent and the command output. It runs the command, filters/compresses the noisy output, scrubs secrets, and gives the agent a much shorter, cleaner result, while keeping the full scrubbed log locally if something actually fails. Why I like it: - Less token waste - Cleaner agent context - Fewer forced compacts - Better signal-to-noise during long coding sessions - Open source, free, installs in a few lines This is one of those tiny infra/devtools things that feels boring… Until you realize it directly improves the way your AI coding agent thinks. Repo: github.com/pivanov/ctx-wire Install: ctx-wire.dev/ Cut the noise. Keep the context. Well done @ivanovpavel

Push is a retention lever. Not a loudspeaker. If every team can send, users will mute. - Segment by intent. - Cap frequency globally. - Deep link to the exact moment. That’s how push drives trust, not opt outs. Read the full playbook 👉 sashido.io/en/blog/push-noti…

Vibe Coding is the future

I asked @Claude Code to build me a @cursor_ai alternative. It built it in #Vim. Free. Open source. Runs over SSH. github.com/mignev/vimsor

🎉🎉🎉

Hello guys, I’m starting a new product. @contentshipio is about how content actually wins in 2026, not just by shipping more pages, but by proof, demand, and trust across Google and LLMs. If you care about SEO beyond hacks, follow along 👇