I'm not crying, I am not...I am...!
Through the VOICE trial, Terry is using his Neuralink implant to help fine-tune a brain-to-voice interface for himself and others who can’t speak. He trained the algorithm first by miming speech as best he could, then by simply thinking the words and hearing them come out in his own natural voice.
Powered by Grok Voice from @SpaceXAI
Powered by Grok Voice ❤️
x.ai/voice
watch us speedrun building a company in 3 days with Grok @Bot!
we'll have some cool special guests coming too
nitter.cf/i/broadcasts/1AxRnZbVp…
Grok Voice is live on fal.
The latest speech model from @SpaceXAI that answers in 0.70 seconds and finishes its tool calls before the sentence ends. Transcription with word-level timestamps, text to speech in 30+ voices across 25+ languages, and cloning from two minutes of audio.
Every voice in this video is from Grok Voice.
Use Grok Voice in fal to build intelligent, low-latency agents that resolve real customer issues
Grok Voice is live on fal.
The latest speech model from @SpaceXAI that answers in 0.70 seconds and finishes its tool calls before the sentence ends. Transcription with word-level timestamps, text to speech in 30+ voices across 25+ languages, and cloning from two minutes of audio.
Every voice in this video is from Grok Voice.
Our team spent many hours working on the Grok Build experience in Warp. Awesome to see an expansion beyond what I had thought was possible!!! 🚀
Venky Yerneni retweeted
Introducing Projects, a new way of working in Cursor.
Rather than creating a chat for every task, you work with a coordinator agent in a single, persistent thread.
Like @bot, your agent is always on, proactively manages work with subagents, and improves over time.
shipped /learn today!
grok will read all your traces locally, find what you repeat, when you intervene, and proposes harness updates in the form of:
- new skills from repeated phrases
- fixes to stale ones
- deletion of unused skills/plugins/mcps
it's fully interactive. feel free to leave feedback in the comments!!
nitter.cf/aksheyd/status/2096364…
Not enough people use /create-workflow in grok build!
Today, it saved me 10k+ tokens by updating the harness (my plugins) to learn from how I've been using it. Here's how:
I told grok to /create-workflow to map reduce every single trace on my laptop to find:
- repeated phrases I can turn into skills (made 2 new ones)
- skills i should update since the codebase has changed (updated 10)
- plugins/mcps/skills I don't use I can delete (deleted 50+!!)
My prompt was:
```
/create-workflow to read EVERY single traces in my ~/.grok. One agent should read one trace itself and explain what it found: phrases OUTSIDE of skills, skills used (which ones + count), mcps used + count, area of the codebase and type of PR I was making (feature, bug fix, etc), and so on.
Then, have one agent for every 10 traces map reduce this information alongside context from the codebase (e.g. skill filepath references) over and over again until we get a synthesis of:
- repeated phrases I can turn into skills OR add into my pre-existing skills
- skills i need to update since they are old
- plugins/mcps/skills with low usage I can delete
Present this information as a concise report that we can actionably work on together (present a short version to me and a fully fledged markdown doc in /tmp for yourself). We will then make these changes after I confirm.
```
I need to iterate a little more, but I'll ship this as a /learn skill soon :0
Hear directly from the legendary @romanugarte_ on Grok Bot!
Grok @Bot is the hottest new AI product in the world right now. I'm absolutely hooked.
It all started a few months ago as a tiny team holed up in a separate part of the office, building from scratch.
Four weeks after the first line of code, the whole company was obsessed. Three weeks later, it launched to the world. Less than a month in, millions of Grok Bots are already helping people get work done.
Roman Ugarte (@romanugarte_) incubated, launched, and now leads product for Grok Bot. This is the first time he's told the story:
🔸 Why they started fresh instead of building it into Cursor
🔸 The two non-obvious bets that made it such a success
🔸 What they learned from manually onboarding the first 200–300 users
🔸 Why they spent the weeks before launch *unshipping* features
🔸 The first prompt to try when you open it
Watch the full episode right here on X 👇