20 | playing with ai agents
Joined November 2024
- Tweets542
- Following3.2K
- Followers6.4K
- Likes13.6K
Rucha Patil retweeted
Introducing Hugo: the first human companion robot.
At Boston Dynamics, I was Chief Strategy Officer, bringing robots into the real world.
My co-founder, Farbod Farshidian, led research at the RAI Institute.
Together, 15+ years teaching robots to run, jump, and work.
So we asked: what if robots could connect with people?
Hugo runs on the first Vision-Language-Expression (VLE) model.
He links what he sees and hears to movement, expression, and gesture.
He notices you, reads the room, and reacts in real time.
And he's only the first.
Dynamic Creatures is @BostonDynamics' official entertainment and hospitality partner.
We're building a cast of characters with film studios, resorts, and theme parks.
dynamiccreatures.com
Rucha Patil retweeted
since you guys asked "what am I looking at" a lot yesterday
here's the code review use case for Jev images, explained better
With agent PRs I want proof it works, and the starting point for UIs is a screenshot in the PR
Even if it works, we still care about understanding the underlying change so we keep a sharp mental model of the software system.
So @ColdteaAI's PR Lens lays out the architecture on a canvas, and Jev matches each PR screenshot to the underlying system components that changed
you review the PR starting from what you can see, its impact on your system's architecture and keep that mental model long before you read a line of code!
try it on your next PR: github.com/coldteadotai/pr-l…
best code review use case for Jev images so far:
PR screenshot in, the architecture and data flow behind it matched
screenshot to matches in ~2 seconds
Try it on your next PR: github.com/coldteadotai/pr-l…
i’ve spent so much time opening files just to figure out which component is in a screenshot
that’s why PR Lens caught my attention. it connects the screenshot to the relevant parts of the app, so you can get straight to the actual changes instead of digging through files
since you guys asked "what am I looking at" a lot yesterday
here's the code review use case for Jev images, explained better
With agent PRs I want proof it works, and the starting point for UIs is a screenshot in the PR
Even if it works, we still care about understanding the underlying change so we keep a sharp mental model of the software system.
So @ColdteaAI's PR Lens lays out the architecture on a canvas, and Jev matches each PR screenshot to the underlying system components that changed
you review the PR starting from what you can see, its impact on your system's architecture and keep that mental model long before you read a line of code!
try it on your next PR: github.com/coldteadotai/pr-l…
Rucha Patil retweeted
Your next AI upgrade might be something you can hold.
Meet SlashVibe, a physical controller for your AI agents.
See agent status at a glance. Switch between agents with a flick. Speak your next instruction.
Keep your agents moving with less window juggling and fewer interruptions.
Coming to Kickstarter October 27.
Get Early Bird Access → slashvibe.ai/
Rucha Patil retweeted
We’ve raised a $10M Series A to automate video creation for every company.
1,000+ organizations like Atlassian, GitLab, Samsara, Legrand, and Zendesk use @clueso to automate their videos for marketing, customer education, and employee training.
The struggle of video creation in companies is so real, that Netflix made a documentary about it
Teams switching TTS providers get 3 months covered. That's an aggressive move
$52M seed round. 15M+ users. But this is what we're most proud of yet.
Introducing Drama 3: the most emotive and controllable TTS model in the world
And yes, it's open-weight.
You can now control how even a single word should sound, change its tone, and shift your voice mid-sentence.
Uncle Roger was impressed too.
Try it here:
s.fish.audio/rqh0l8
Comment “DRAMA” within the next 48 hours for 1 month free.
If you're an enterprise your first month is on us:
s.fish.audio/qz9r0t
Rucha Patil retweeted
$52M seed round. 15M+ users. But this is what we're most proud of yet.
Introducing Drama 3: the most emotive and controllable TTS model in the world
And yes, it's open-weight.
You can now control how even a single word should sound, change its tone, and shift your voice mid-sentence.
Uncle Roger was impressed too.
Try it here:
s.fish.audio/rqh0l8
Comment “DRAMA” within the next 48 hours for 1 month free.
If you're an enterprise your first month is on us:
s.fish.audio/qz9r0t
Rucha Patil retweeted
Introducing SubQ Snap, the first long-context decision model for real enterprise work.
Snap is the only decision model or LLM where compute per token stays constant as context grows.
• 384K tokens of multimodal context, 12x larger than Jev.
• 61.7 on Decision Index v0.2.1 vs Jev’s 57.9, outperforming on 13 of 16 enterprise benchmarks.
•Processes 100K tokens and returns a decision in under one second.
•$0.05/MM input tokens. Output is free.
Available today to anyone.
The first 10,000 sign-ups get 100M free input tokens.
We’ll likely hit capacity fast and will add users as we add compute. Compute offers welcome 🙂.
Latency will be variable as we tune the platform to this new model and category of users.
Model speeds are 80ms for minimal context, 250ms for 32k, 660ms for 100k, and 2.5 seconds for 384k.
Visit: subq.ai/
The keyboard is going to be the fax machine of the 2030s
we've raised $50M from Khosla Ventures, Accel, Initialized, Kevin Weil, DST Global
to build the world's most wearable BCI cap at Sabi
read more here:
forbes.com/sites/rashishriva…
well, there goes my whole night
Nano Banana 2.1 is live on ElevenCreative.
Google's image generation and editing model brings faster generations, better visual design, and subject consistency.
Try it now: elevenlabs.io/creative
wait, so every agent gets its own identity but still stays linked to the person running it?
basically “sign in with google” for ai agents
ngl, that’s pretty damn cool
Introducing AgentID by @agentmail, "Sign in with Google" for AI Agents
Millions of agents already use AgentMail. AgentID lets them sign in to your app.
Integrate with the prompt below, reply with a screenshot, and we'll give you 3 months free of any AgentMail plan.
this is way more interesting than just another text-to-video model
spira maxima is being trained around what actually works on social, not just what looks good in a demo
you give it an idea and it handles the presenter, b-roll, motion, captions, music, and the rest of the post-ready video
if it can consistently make videos people actually want to watch, this could be a really useful workflow
🤝 Paid partnership
Introducing Spira Maxima 1.0, the most complete text-to-social-video model.
Spira Maxima turns plain text into a finished social video: presenter, on-trend B-roll, motion, captions and music, ready to post and get traffic.
Unlike other video gen models, Spira Maxima is post-trained on trending videos and performance data, so every generation follows what is working on the feed right now.
We generated thousands of videos yesterday and took the #1 spot on launch day by a wide margin.
We're open-sourcing it when this post hits 2M views or @SpiraAI reaches 5K followers.
We'll drop some examples and videos in the comments, try it and leave you thoughts: spira.ai