I've left most of what I want to say in the VoidZero blog post. But worth repeating:
Thank you @voidzerodev team for trusting me and joining me on this wild ride. I am very proud to have assembled such a talented team and even prouder of what we have built together.
Thank you all our investors for believing in my vision, in particular @caseyaylward from @Accel who led both our Seed and Series A.
Thank you the @vite_js community. Vite and VoidZero wouldn’t have come this far without your trust and support. We will continue building with all of you, together, in the open.
And thank you to everyone that made this happen at @Cloudflare. Looking forward to working with you all!
https://t.co/0ly53VCOSr
@mitsuhiko@MoulikTweets For slack (chat) or google doc (collaborative editing) like experience, wouldn’t websocket still be the best choice at the moment?
@ericzakariasson Couldn’t get atlassian and slack connected in cursor cloud agent. It needs something as easy as Claude connectors. I had to switch to Claude every time I need to interact with those.
@bygregorr@ivanfioravanti@ActuallyIsaak My understanding is that fine tuning allows you to utilize smaller (hence faster&cheaper) model to achieve same quality as the larger model when you know the task is niche/specialized enough.
@julien_c@iamharishvasu@huggingface I don’t understand. I had the same plan for my last few flights - run local model for fun/coding. Then I found all those flights had free WiFi now🤡. Since then, the only justification for local LLM I can see is privacy or security (when cloud LLM is down).
@rishabh_sambare@tokifyi wait, are you serious. Omg, how could I not know this before. I thought the founder is seasoned SE before it. (Not saying coop is not seasoned, but you know what I mean)