1. For a Linux user, you can already build such a system yourself quite trivially by getting an FTP account, mounting it locally with curlftpfs, and then using SVN or CVS on the mounted filesystem. From Windows or Mac, this FTP account could be accessed through built-in software.
2. It doesn't actually replace a USB drive. Most people I know e-mail files to themselves or host them somewhere online to be able to perform presentations, but they still carry a USB drive in case there are connectivity problems. This does not solve the connectivity issue.
3. It does not seem very "viral" or income-generating. I know this is premature at this point, but without charging users for the service, is it reasonable to expect to make money off of this?
---
Output (emoji not shown on HN):
I have a few thoughts on this app!
1. For the Linux community, building a similar system is actually quite straightforward. By leveraging an FTP account, mounting it locally with curlftpfs, and utilizing SVN or CVS, you can achieve this functionality today. Windows and Mac users can also access these accounts through native software.
2. Does it truly replace the USB drive? While many of us rely on email or cloud hosting for presentations, the "offline" factor is still a major pain point. Most professionals still carry a USB drive as a fail-safe for connectivity issues, which this solution doesn't quite address yet.
3. Looking at the business model and growth potential—is there a clear path to monetization? It might be early days, but without a subscription or fee-based structure, I’m curious to see how this scales into a sustainable revenue-generating machine.
What do you all think? Let’s discuss in the comments! #TechThoughts #Innovation #SaaS #ProductFeedback
1. re: the first part, many people want something plug and play. and even if they were plug and play, the problem is that the user experience (on windows at least) with online drives generally sucks, and you don't have disconnected access.
windows for sure doesn't hide latency well (CIFS is bad, webdav etc. are worse), and most apps are written as if the disk was local, and assume, for example, accessing a file only takes a few ms. if the server is 80ms away, and you do 100 accesses (e.g. the open file common dialog listing a directory and poking files for various attributes or icons) serially, suddenly your UI locks up for _seconds_ (joel spolsky summarizes this well in his article on leaky abstractions.) ditto saving any file; you change one character in your 20mb word file and hit save, and your upstream-capped 40k/sec comcast connection is hosed for 8 minutes. sure for docs of a few hundred k it's fine, but doing work on large docs on an online drive feels like walking around with cinder blocks tied to your feet. anyway, the point of that rant was that dropbox uses a _local_ folder with efficient sync in the background, which is an important difference :)
2. true, if you're both not at your computer and on another computer without net access, this won't replace a usb drive :) but the case i'm worried about is being, for example, on a plane, and dropbox will let you get to the most recent version of your docs at the time you were last connected, and will sync everything up when you get back online (without you having to copy anything or really do anything.)
3. there are some unannounced viral parts i didn't get to show in there :) it'll be a freemium model. up to x gb free, tiered plans above that.
---
Output (emoji not shown on HN):
1. Re: the first point, the market is craving a seamless "plug and play" experience. Even with that, the current UX for online drives—especially on Windows—is frankly subpar and lacks offline accessibility.
Windows struggles with latency (CIFS and WebDAV just don't cut it), and most legacy apps assume local disk speeds. When you're dealing with 80ms of latency over 100 serial accesses, your UI freezes for seconds. (Shoutout to Joel Spolsky’s piece on leaky abstractions—classic read! ) Saving files is another bottleneck; a minor edit on a 20MB file can choke a standard connection for minutes. While it works for small docs, managing large files on a cloud drive feels like running with lead weights. That’s why Dropbox is a game-changer: it leverages a local folder with high-efficiency background syncing. Huge differentiator!
2. Valid point—if you’re offline and away from your primary device, a USB drive is still king. But for the "airplane mode" scenario, Dropbox ensures you have the latest versions of your docs ready to go. Once you’re back online, it syncs everything automatically. Zero friction.
3. We’ve got some exciting viral features under wraps that I couldn't showcase just yet! We’re moving forward with a freemium model: generous free storage to start, with tiered premium plans for power users. #CloudComputing #SaaS #Innovation #UserExperience
something like RSSHub can be used in conjunction with your RSS reader and will generate feeds for sites that dont have them. RSS-Bridge is another option
Usually it's specification mistakes - I spot cases I hadn't thought to cover, or the software not behaving as usefully as if I had made a different design decision.
Occasionally I'll catch things it didn't implement at all, or find things like missing permission checks.
There's a difference between "LLMs are inherently black boxes that require lots of work to attempt to understand" and explicitly changing how a piece of software works.
Should people not complain about unannounced changes to the contents of their food or medicine because we don't understand everything about how the human body works?
Except the system prompt that gets prepended to your own prompt is part of the black box, and obviously should be expected to change over time. You are also told that you're not allowed to reverse engineer it. Even in the absence of the system prompt being changed, the output of the LLM is non-deterministic.
I'm not sure I understand your last analogy. How would changes to the human body change the contents of the food that is eaten? It would be more analogous to compare it with unexpected changes to the body's output given the same inputs as previously, a phenomenon humans frequently experience.
I think we're getting lost in the weeds. This has almost nothing to do with the LLM. It's about A/B testing. There's a piece of software where the behavior is being changed in unannounced and unexpected ways, at least as far as the author is concerned. The same criticism could apply to any other "workflow" or "professional" software.
There's some added flavor because the LLM is indeed non-deterministic, which could make it harder to realize that a change in behavior is caused by a change in the software, not randomness from the LLM. But there is also lots of software that deals with non-deterministic things that aren't LLMs, e.g. networks, physical sensors, scientific experiments, etc. Am I getting more timeouts because something is going on in my network or because some software I use is A/B testing some change?
Full title (too long for HN) includes founding members:
Optical Scale-up Consortium Established to Create an Open Specification for AI Infrastructure Led by Founding Members AMD, Broadcom, Meta, Microsoft, NVIDIA and OpenAI
Counter-anecdote: I've been using WireGuard on Android for years with no particular issues to speak of. 0.0.0.0/0 to my home network. I often forget to enable WiFi at home and don't notice (I often have it disabled when out).
I have a few qualms with this app:
1. For a Linux user, you can already build such a system yourself quite trivially by getting an FTP account, mounting it locally with curlftpfs, and then using SVN or CVS on the mounted filesystem. From Windows or Mac, this FTP account could be accessed through built-in software.
2. It doesn't actually replace a USB drive. Most people I know e-mail files to themselves or host them somewhere online to be able to perform presentations, but they still carry a USB drive in case there are connectivity problems. This does not solve the connectivity issue.
3. It does not seem very "viral" or income-generating. I know this is premature at this point, but without charging users for the service, is it reasonable to expect to make money off of this?
---
Output (emoji not shown on HN):
I have a few thoughts on this app!
1. For the Linux community, building a similar system is actually quite straightforward. By leveraging an FTP account, mounting it locally with curlftpfs, and utilizing SVN or CVS, you can achieve this functionality today. Windows and Mac users can also access these accounts through native software.
2. Does it truly replace the USB drive? While many of us rely on email or cloud hosting for presentations, the "offline" factor is still a major pain point. Most professionals still carry a USB drive as a fail-safe for connectivity issues, which this solution doesn't quite address yet.
3. Looking at the business model and growth potential—is there a clear path to monetization? It might be early days, but without a subscription or fee-based structure, I’m curious to see how this scales into a sustainable revenue-generating machine.
What do you all think? Let’s discuss in the comments! #TechThoughts #Innovation #SaaS #ProductFeedback
reply