AI is speeding up. 7x up in just this instance. Today's lesson from NVIDIA's GTC? AI factories are generating tokens faster and cheaper than last year and that's making new things possible. I'm feeling it, as I use AI to make a new X news site that we'll turn on this weekend.
SOFTWARE
-
Developer Uses Claude Code on VPS via Tailscale SSH Workflow
By
–
It's @TermiusHQ + Mosh + regular SSH to my @hetzner_online VPS via Tailscale Then I just installed Claude Code on there and code on my sites via that!
-
Claude Code Builds Hoodmaps Integration for Airbnb Neighborhood Search
By
–
This was asked for for YEARS and I could never find time to build it myself
— @levelsio (@levelsio) 17 mars 2026
🗺️ Hoodmaps for 🏡 Airbnb
Hoodmaps is my app that lets you find out where to stay in a city, it classifies neighborhoods by:
🟥 Tourists
🟨 Cool
🟩 Rich
🟦 Suits
⬜️ Normies
I asked Claude Code to… pic.twitter.com/vSmfllMR0vThis was asked for for YEARS and I could never find time to build it myself Hoodmaps for Airbnb Hoodmaps is my app that lets you find out where to stay in a city, it classifies neighborhoods by: Tourists Cool Rich Suits Normies I asked Claude Code to
-
AI Shifts Bottleneck from Code Generation to Code Review
By
–
The bottleneck has so quickly moved from code generation to code review that it is actually a bit jarring. None of the current systems / norms are setup for this world yet.
-
Codex Adds Robust Transcript Export Options Multiple Formats
By
–
Robust options for exporting transcripts in a variety of formats and levels of detail, from both Codex CLI and Codex Cloud
-
Claude Code Used to Set Up Q3JS ioquake Server on Linux
By
–
This is Q3JS with runs an ioquake server on Linux and I think Q3JS is a Next JS app in a Docker I just asked Claude Code to set it up 😀
-
Copilot Cowork vs Chat: Model Agnostic Performance Analysis
By
–
I said Copilot Cowork not Copilot Chat, which is model agnostic (and consistently behind because of it, I’d add)
-
Grok’s Text to Speech API Now Available in LiveKit Inference
By
–
Grok's Text to Speech API is now available in LiveKit Inference.
— LiveKit (@livekit) 16 mars 2026
Natural, expressive voices with low-latency streaming. Multilingual in 20+ languages. Telephony and production-ready out of the box.
One API key. No extra setup.
→ https://t.co/LCX4zfQTg8 https://t.co/qgUSVDgLoY pic.twitter.com/w9s1QuirbcGrok's Text to Speech API is now available in LiveKit Inference. Natural, expressive voices with low-latency streaming. Multilingual in 20+ languages. Telephony and production-ready out of the box. One API key. No extra setup. → docs.livekit.io/agents/model… xAI (@xai) Grok's Text to Speech API is now available. Start building with natural voices and expressive controls to bring your apps to life. x.ai/api/voice#text-to-speec… — https://nitter.net/xai/status/2033617157884678507#m [Translated from EN to English]
-
Generative AI System Fails to Produce Output for a Year
By
–
Move to the Netherlands
— @levelsio (@levelsio) 16 mars 2026
We will just tell you https://t.co/DQTiqdIq9SMove to the Netherlands We will just tell you
-
Subagents Now Available in Codex for Workflow Acceleration
By
–
Hello subagents in codex. Have seen some awesome new and creative workflows emerge from thesehttps://t.co/kw1ua4QjMh https://t.co/ppWRCfIswe
— Tibo (@thsottiaux) 16 mars 2026Hello subagents in codex. Have seen some awesome new and creative workflows emerge from these Subagents are now available in Codex. You can accelerate your workflow by spinning up specialized agents to:
• Keep your main context window clean
• Tackle different parts of a task in parallel
• Steer individual agents as work unfolds