That's really interesting. Let me know if you'd want to talk to me or Michael sometime about it. With the models we run currently, you'd really have to have a GPU to run locally and get a lot of utility. I'm curious if you have some thoughts on how to run these large language models on edge devices.
I'm wilson@ our website (trying to avoid too much spam from bots).
I just checked into it. I think the misunderstanding is that force enable only enables autocomplete. Compose Now and Rephrase still misbehave on the majority of websites and make them hard to use, so we didn't include them in the force enable functionality. There's a note about it on the Notion doc Michael linked, but that isn't clear enough in the product. Thanks for letting us know! I'll fix that!
Let me know if you're actually not seeing Github show autocomplete either. I'd love to debug that, but I checked again and it seems to be working for me right now.
I'm curious what you mean by "also tried Compose.AI to compose this message but all suggestions just threw away some of the info"
Compose.ai (YC W21) | Senior Frontend Engineer | Full Time | REMOTE | $100k-150k | Meaningful Equity (0-2%)
We're a small team (5 full time, 7 total) with a big mission that involves many interesting technical challenges. In particular, we're bringing real-time, personalized, suggestions to users on every keystroke across every website while aiming to reduce typing by 40%. We're looking for someone to join as a core member of our team as we continue to grow and navigate product-market fit.
We are mainly looking for an experienced frontend-stack engineer to help our team create a stunning experience across all of our users' tools as well as expand our Chrome Extension to more websites in a scalable way. We need your help to make our mission a reality: amplify human potential by bringing intelligence to human-computer communication. Providing AI-powered autocompletion across all of your tools and devices is just the start.
If you're interested or you may know someone who would be, please check out or forward the roles below
I've added you as a candidate for the Senior Frontend Developer role. I assume that would be the best fit?
For others reading this, a CV is not necessary to apply (though helps me quickly and accurately screen). All we require at first is your name, email, and a response regarding our quick quiz on the Lever page (just whether you have already completed it or will complete it).
Compose.ai (YC W21) | Senior Frontend Engineer | Full Time | REMOTE | $100k-150k | Meaningful Equity (0-2%)
We're a small team (4 full time, 7 total) with a big mission that involves many interesting technical challenges. In particular, we're bringing real-time, personalized, suggestions to users on every keystroke across every website while aiming to reduce typing by 40%. We're looking for someone to join as a core member of our team as we continue to grow and navigate product-market fit.
We are mainly looking for an experienced frontend-stack engineer to help our team create a stunning experience across all of our users' tools as well as expand our Chrome Extension to more websites in a scalable way. We need your help to make our mission a reality: amplify human potential by bringing intelligence to human-computer communication. Providing AI-powered autocompletion across all of your tools and devices is just the start.
We're also looking for a product designer (part-time or contract) to work closely with the founders in exploring new ideas, fleshing out requirements, clear up ambiguity, and ultimately create mockups/sketches that our engineers can use to implement quickly. We are looking for someone who leans a bit more into the product and UX side of design rather than a master of visual design.
If you're interested or you may know someone who would be, please check out or forward the roles below
Will publish it on my Github tonight (Japan time), mitchellw, then work on putting it in spacemacs develop branch when I can. It's crazy simple right now (just loads fennel-mode defines a few spacemacs-style keybindings for things available in that mode).
Oh very nice. I will check that out more later. Definitely love the concept and would be interested in hearing if you have any future plans. I thought it could be cool to define major and minor modes like emacs that you could also "autoload" based on application names or types or even use what monitors are plugged in/wifi/times of day to switch. I suppose you have major modes already with what application is focused.
A Spacehammer REPL would be huge for prototyping/developing new features in Fennel. My github is mitchellw. Would love to help out :)
I recently picked up this tool and picked up someone's config that does some modal keybindings similar to spacemacs [1]. It actually inspired me to hack around with their config and then write a spacemacs layer for fennel-mode which someone had written a decent version of already [2]. I'm a bit of an emacs and fennel noob, but it seemed like a fun little problem to solve. I'm especially interested in getting autocomplete working better. I've been trying to base things off of other lisps' layers, but all ears for any tips on how to approach it. I'll edit in my github later as I have everything local at the moment.
I'm wilson@ our website (trying to avoid too much spam from bots).