I've officially left https://t.co/MD2Xc5heDO
I've had a good rest, with plenty of time for travel & tinkering, and now I'm thinking about what to do next. I've got a few ideas to share soon, but I'm also open to suggestions - feel free to reach out :)
I've been using SolveIt for over 18 months, and have created more than 600 dialogs. It's changed how I work day-to-day, forever.
I'd urge you to try it too. But why? Why should you bother? Take a look at the video to see if it's for you (spoiler - it is). 🙂
https://t.co/q0bFKH6S37
Step 3 to achieve truly serverless GPUs for AI inference: skip over application setup work by saving processes to storage and then reloading them instead of re-executing them.
Open source Jarvis that runs on a single GPU
Today we're releasing the vui stack. A local voice agent that you can chat with in real time, with tools and can run claude to do more complex tasks.
Inside this stack is the new vui nano model, a 300M TTS model that can render audio in reply to what you've said and supports a variety of non speech sounds.
vui nano speaks with you, not at you.
The stack can run on as little as 6GB of vram.
Voice cloning supported with prompts of up to 5 minutes. The longer the better.
A voice for your openclaw with our v1/realtime endpoint.
I have developed this on my own so would love to get the communities feedback and help improving it.
Please retweet this so that everyone knows they can have their own private Jarvis
Topic of stream today:
- How do agent harnesses work
- How does one secure them
- How do you test them
This is not Zach teaches. This is we have Cursor up, chat with code, and learn these together.
Come join at 11am EST!
https://t.co/tnCudkl2lo
Agent harnesses reach the many when the models inside them are efficient.
Our goal: compress frontier-grade skills into a footprint small enough to run unquantized on lightweight compute.
Zooming out, most know us as the NFT storage company. But, that's just a market we serve.
Our internal core competency is hosting a difficult open-source protocol (IPFS) and making it easy for anyone to use.
When OpenClaw came along, we felt it matched our core competency perfectly. It's a difficult open-source protocol that we want to make easy for anyone to use.
@KyleTut I don't have a good answer for this yet, but there is a big opportunity optimizing what context is being used at any time for a new prompt. Somehow, we need to determine how to compress more context into a smaller space. Encoding context as embedding maybe?
@namedotcom I have received no response from the team and am still not getting emails. Can you at least tell me if this is a problem for just me or all https://t.co/BVjfVcootg email forwarding?
Does anybody use @namedotcom email forwarding service? I have been having issues receiving emails today but the support person said I was the only one complaining. Can anybody confirm their email forwarding is working?
@namedotcom any update on this? I am still not getting any emails and I haven't heard if you tried using the email forwarding on another domain and have confirmed this is only an issue on my account.
@namedotcom This is a quiet failure so it is possible that other people haven't realized it is broken yet and that is why you haven't received other tickets regarding this rather than it being specific to me.
@namedotcom Ok, can you please just ask them to test email forwarding on another account that has it set up? I would just like confirmation that this is actually a problem specific to my account.
@blingdivinity Solveit does what you're describing but I am not sure it is publicly available yet. If you decide to go for it, you can use my referral link to get a 15% discount https://t.co/rc5QShHwJS
I think it's worth it, but I've been a user for over a year now and use it every day