I made Say for Codex.
Type `/say` after an answer and Codex reads it aloud locally on macOS.
No API key.
No sending text to a TTS model.
No pasting long reports back into chat.
Useful when you want to listen while reading, or review long agent output hands-free.
Link below.
https://t.co/c8FuKb0jUg
@ClaudeDevs I was planning to subscribe just to try it out and get one task done, well, I missed that chance. Let’s see if another open source model can change that. Obviously from the Chinese labs.
I built a tiny Codex skill for local read-aloud on macOS.
It lets Codex read answers, clipboard text, and Markdown files aloud using macOS speech, no API key needed.
Useful for cognitive offloading: read + listen at the same time.
GitHub:
https://t.co/29E86SHVuV
Your vibe design partner just got more collaborative!
To celebrate I/O, here are 5 major upgrades (and one big bonus!):
🌊 Streaming
📄 Start with your existing design
⏩ In-place AI Edits
🎥 Motion on HTML-native Canvas
🚀 More Import / Export Options (.fig, Netlify, Loveable, Bolt)
🌟 BONUS: Import and sync your codebase
Rolling out now. Details and product walkthrough video in 🧵
Nemotron 3 Ultra was launched today, including a focus on low latency agentic performance. We tested it against peers under restricted turn-usage limits on Terminal-Bench v2.1 - @NVIDIA Nemotron 3 Ultra completes tasks at a much faster pace than peers due to its high inference speed while scoring competitively on the benchmark.
In this analysis each model is given a ‘turn limit’ within which it can complete tasks, inside a customized version of the Terminus 2 harness which advises it of this limit. We apply 4 increasing turn limits and trace each result’s tradeoff of task latency and performance. Time per task, on the X axis, is calculated as decode time based on token usage and measured endpoint output speeds (for Nemotron 3 Ultra, speeds were measured on a pre-release deployment on @blackboxai), plus the actual time spent executing tools to complete the benchmark.
Nemotron 3 Ultra is the fastest across all turn limits and sits on the Pareto frontier for performance versus time per task for this evaluation.
We’re thrilled to announce the Antigravity CLI, a lightweight way to spin up the same Antigravity agents right from the terminal. 💻
It gives you the exact same harness and same models, with a product experience tailored for the command line. It adapts entirely to you: your keybindings, your themes, your workflows.
Full Antigravity CLI Walkthrough: