I don't understand how these type of projects are still tried and get any traction... anyone who has tried them will 100% know it won't go beyond a happy path demo. If they want to seriously use/publish the app beyond playing around, it'll require weeks of iteration via AI, which will cost you an arm and a leg in tokens.
Founder of Raycast here so obviously biased but you’ll be surprised. You get a working app one-shotted pretty much all the time. Sure if it is something more complex you might need a few more prompts. Just to give you some examples on what we’ve seen:
- Our support team runs on Glaze apps to review Raycast extensions. It connects to GitHub, checks out code locally, gets realtime updates and so on.
- The sound agency build a functioning synthesiser for the launch video. It works even with MIDI.
- We’re about to cancel a team-wide subscription and replace it with a Glaze app.
Not everything is possible yet and sure more complex things need more prompts but you’ll be surprised what Glaze is capable of already. It’s day one…
Sales are about distribution, they have a channel. This "moat" thing matters to unestablished start-ups a lot more. We should apply context while copy pasting arguments.
This just means that the existing sales channel would be their moat. Which can be a valid argument, though I don't remember having heard of Raycast before, so it isn't obvious to me. I was interested in hearing what they see as their moat here.
This sounds promising. If I may take advantage of you being here, what language does it write in? Does it build genuine native apps (Cocoa, WinAPI or WinUI, etc) or Electron?
The FAQ was light on technical details. But I am someone keen to read all the technical details :)
I assume there is an extensive set of rails for the agent to tie into. (Compare this to asking Claude to green fields an app. Do you use electron? How are notifications handled? Icons? Permissions?)
It springboard off Raycast’s teams feature so well it actually gives it a real reason to exist. You’re empowering the one systems thinker in the group to export their automations to the rest of the group in a way that’s proven to work: small apps that do one thing. (Big apps get complicated, become full time projects that distract from the task at hand)
Fig tried this but it was just for engineers, the value prop was missing, Glaze seems to get this right.
What kind of application are you thinking off? We build fairly complex applications in days for our clients, from presentation to launch. These are not trivial applications or landing pages; accountancy, payments (banking), erp, hrm backends, portals and mobile apps.
I haven't used v0 or replit before, I have the same feelings as you. But I've been thinking about building macOS apps for my personal use for a long time now. Also I'm a long time Raycast user. I have a bias here, so I've joined the waitlist, I can't be sure until I try, right?
Just build Mac apps then. Claude Code can help you whip up real native apps without any Glaze dependencies just fine. I’ve built 4 Mac and iOS apps in the last 6 months for my own use. I even have my own HN app for iOS and Mac.
Even if you don't like Electron, I was able to get Claude to build Electrobun and Tauri apps as well. I don't understand what benefit Glaze will bring outside of more lock-in?
100% agree. My default is also DuckDuckGo, but I know for a fact that if the search is anything other than finding the homepage of a company, I'm gonna struggle with duck. I still use it because I want to not use Google, but Google is 10000000% a superior product.
Google Docs is a document editor (opening/saving Microsoft office compatible documents, with layout, etc), not a wiki/markdown editor. The La Suite Docs seems a product more similar to Atlassian Confluence.
> (opening/saving Microsoft office compatible documents, with layout, etc)
Not being Microsoft Office®-compatible does not make something not an office suite. In that case, there is (by design) only one Office® suite in the world
> not a wiki/markdown editor
I was wondering if you meant WYSIWYG editing as opposed to markdown editing, but then you say
> La Suite Docs seems a product more similar to Atlassian Confluence
which is WYSIWYG (the best web-based wysiwyg editor I've ever used, in fact; even if I'd never choose it for being a vendor lock-in that has shown they want to own your data by removing the self-hosted options, maybe with exceptions for giant enterprises idk but at least we had to migrate and it wasn't fun)
so then what are you saying? What makes an 'office suite' an office suite to you?
Not the OP, but I would think most people would expect to see a word processor, a spreadsheet, some kind of presentation tool, and maybe a simple database. That's not just comparing to MS Office, that's LibreOffice as well? La Suite seems to have more and better collaboration tools than LO, but it is also less document-focused, just looking through their repos.
> Google Docs is a document editor (opening/saving Microsoft office compatible documents, with layout, etc), not a wiki/markdown editor. The La Suite Docs seems a product more similar to Atlassian Confluence.
In the last 10 years I've been spending much more time at the office consulting and editing confluence and web pages (sharepoint / mkdocs / readme and other markdown based resources) than the cumulative time spent on
word, excel, powerpoint and pdf documents. I imagine it is the same for a significant portion of the population.
Also, libreoffice is already a thing and nobody edits office365 documents using the web versions except when their employer can't/don't want to pay the license for the full version or the client is not vailable on their OS (linux users). Libreoffice doesn't have that problem, you only really need storage with sharing facilities, not featurefull web clients for your docs.
Spot on this is what we aimed for. Office tools were meant to be printed to be shared. Or at least exported. When you think of it it’s really bad for information security. On the plus side doing everything in the browser manipulating jsons is you get to do way better real time collab and can include a lot more interactive content.
Even when using google docs, I dropped the paper format, and at that point it's better to edit/read in a richer editor like Confluence which has better support for interactive widgets, expand zones, code blocks, etc. It's also been better at navigating a tree of documents.
Google docs is still great when you need to make something you mean to print, it just tends to not be that often anymore.
I even use markdown shortcuts to format in google docs nowadays.
For layouts and opening docs from other suites, it seems they rely on OnlyOffice, as listed on the marketing page of their Google Drive equivalent [1]. OpenDesk from ZenDiS (German counterpart to this project, also collaborating on La Suite) seems to rely on Nextcloud and Collabora Online for that [2]. Collabora and OnlyOffice are also present in Lasuite Drive's development environment [3].
Docs and Drive aren't the only products in this suite: they also provide alternative for Meet, Chat, GMail or Sheets. I have no doubt that Microsoft and Google products offer more features but my point still stands: a lot of employees (like myself) need productivity tools but only need the core features.
I guess I am a markdown hater, but I don't like it. Markdown feels too much like hand writing your own html, when you have to put in tags, but like html it suffers from lack of layout control, which is why they invented CSS, but you don't get CSS control in markdown. If you start adding that, you end up with LaTex, and I don't know anyone who actually enjoyed writing serious documents in Latex. It was fun in the beginning, but it quickly became tiresome and I found myself not being very productive.
Doing layout is not easy. Programming layouts well requires real expertise, which is why most layout engines expose a gui and let you deal with larger text components graphically. Maybe someone else will come up with a usability innovation here, but I'm not aware of it, and markdown certainly doesn't have that capability.
it's truly a bismal experience compared to what else is out there (my experience is with rust, python and ts inside vsc).
Often autocomplete is hopeless and doesn't help you with the most simple things like picking from multiple initializers, or changing to a different signature of a function call.
the project setup is this mystery Xcode project file, instead of a standardized yml or something that anyone can modify and understand.
I have to say provisioning has improved a lot. I remember back in 2008, it was really a pain to get anything working.
This is not necessarily about Xcode, but maybe it should be: screen shots for your app. they need screenshots for 454 device types, and zero automation in their own tooling.
the layout is also very inflexible. they dictate a couple of panels and that's how you _must_ use them. that's unlike any other modern IDE.
Quite sure it's done in order to speed up the camera app performance and reduce the time to first photo time. The camera module requires some tenths of a second to boot up and it makes sense to start that process at the earliest indication of user's interaction.
In this case, a touch-down is a good indication, even if user ends up swiping instead of touch-up.
The same thing happens in the lock screen, if you hold your finger on the lock screen and move 1 pixel to the left, the camera module starts up even if you don't finish your swipe to camera gesture.
Wouldn't surprise me either. I know a guy who worked at Apple on iOS perf and the one time he was telling me about it years ago, it was "camera app doesn't start fast enough, so we reworked memory management". Apple really cares about the camera.
I bet this is in the new version 26. That version is so garbage and I regret updating. 95% of the time, when I open the phone, it doesnt unlock my phone with face and I have to enter PIN. Sometimes I cant take photos also. In the browser, when I touch the address field nothing happens and I can go on and on and on. Just leave the shit as is, people. Its like if I have a screwdriver in my workshot and every other month, when I come back to use it, you change some bullshit, so I have to operate it slightly different. Fuck that
I think ChatGPT has a similar feature. I was amazed how the reply starts coming in literally the moment I press enter. As far as I can tell that is only possible if all the previous tokens I submitted have already been processed. So when I actually submit the message, it only needs to update the inner state by one more token.
i.e. I think it's sending my message to the server continuously, and updating the GPU state with each token (chunk of text) that comes in.
Or maybe their set up is just that good and doesn't actually need any tricks or optimizations? Either way that's very impressive.
The 'flash' / no or low-thinking versions of those models are crazy fast. We often receive full response (not just first token) in less than 1 second via API.
> I think it's sending my message to the server continuously
It is, at least I see it for the first message when starting a new chat. If you open the network tools and type, you can see the text being sent to the servers on every character.
Source, from spending too much time analysing the network calls in ChatGPT to keep using mini models in a free account.
IIRC, apple has a patent from years ago for keeping a camera module in a semi-active mode when the phone isn't entirely idle to make starting it faster.
reply