Staff Developer Advocate @livekit 🥑 | YouTuber | Instructor | Opinions My Own ▶ https://xitter.twitterapi.xyz/t.co/F8KotMcjqF 🦸🏿♀️ Become a https://xitter.twitterapi.xyz/t.co/RbSzdneECZ 🦸🏼♀️
👉
Joined June 2019
- Tweets6.1K
- Following1.3K
- Followers17.6K
- Likes13.2K
Jesse Hall retweeted
Ask your coding agent what's going wrong in your voice agent calls. It will read the logs and hand you a ranked list of what to fix.
Just approve it and it'll fix, test and redeploy.
LiveKit Cloud API is in beta today. No waitlist.
livek.it/2XyuTC6
still trying to figure this out. the job is turning into reading diffs more than writing code. what helps you review agent output faster?
4
6
1,179
i've been testing gemini 4 carbon for a while now. i gave it a prd to build a "jarvis" voice assistant and it did it in 4.5hrs with no prompting from me.
i also had it fix bugs in another open source repo, and look for security vulnerabilities.
results in video, thoughts?
learn more: livek.it/9oJNwBJ
2
6
544
i've been testing gemini 4 carbon for a while now. i gave it a prd to build a "jarvis" voice assistant and it did it in 4.5hrs with no prompting from me.
i also had it fix bugs in another open source repo, and look for security vulnerabilities.
results in video, thoughts?
Jesse Hall retweeted
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
180 simulated callers is how i tested the new voxtral 3 models from mistral
learn more about agent simulations -> livek.it/gkyYVw2
Jesse Hall retweeted
Today, we’re bringing GPT-Image-2.6 to Codex and the API.
Image-2.6 Flare and Sunburst, our two new API image models, generate images 50% faster than before.
At medium or high quality, Sunburst keeps details more consistent from one edit to the next.
i like the accessibility tree approach. screenshots burn tokens and miss state that's already sitting in the ui tree.
curious how agent-desktop handles canvas-heavy stuff like Figma.
Introducing agent-desktop
agent-browser, for your whole computer
→ Computer Use for any coding agent
→ macOS, Windows and Linux
→ Runs in bg while you keep working
→ Agents use your computer in parallel, each with its own cursor
3
6
761
Jesse Hall retweeted
Introducing agent-desktop
agent-browser, for your whole computer
→ Computer Use for any coding agent
→ macOS, Windows and Linux
→ Runs in bg while you keep working
→ Agents use your computer in parallel, each with its own cursor
Jesse Hall retweeted
This is Genie 4, our most realistic and interactive world model yet. 🌐
Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.
Jesse Hall retweeted
GPT-6.1 Terra: delivering fast and capable computer use at a lower price.
GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
🤖 Made with AI
Jesse Hall retweeted
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent.
It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
Jesse Hall retweeted
Voice agents get built three ways: cascaded (STT, LLM, TTS), turn-based speech-to-speech, and full-duplex, where the model listens and talks at the same time.
All three now run on LiveKit Inference: GPT-Live and GPT Realtime from @OpenAI, @grok Voice Think Fast from @xai, and Gemini Live from @GoogleDeepMind. One LiveKit Cloud key, one bill.
Jesse Hall retweeted
Introducing Gemini 4 Argon – our new frontier model.
It’s built for complex workflows across coding, enterprise knowledge work, and cybersecurity defense – rolling out today to a set of trusted testers through our Fairwind Program.
Jesse Hall retweeted
i keep seeing all of these amazing hype reels that people are saying opus 5.5 created with a single prompt.
one shot, yeah right.. liars!! so i tried it.
prompt: "make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are, like it's your showreel for a resume. go all out"
i keep seeing all of these amazing hype reels that people are saying opus 5.5 created with a single prompt.
one shot, yeah right.. liars!! so i tried it.
prompt: "make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are, like it's your showreel for a resume. go all out"