Dynamic content is not the problem. I don't want dynamic content. I think HTTP and servers are the way to go on dynamic content. I just tried, for years, to use IPFS as a way to distribute static content (you know, stuff that will never ever change, even if that stuff is referenced from a dynamic location), and the problems I encountered were so many I finally gave up.
I would love to see all these problems solved and IPFS working very well in the next few years, but I'm afraid the IPFS people are very good in making press releases and presentations, but not in delivering really good software as they say they do.
Anyway, they have no obligation to deliver anything to anyone -- except maybe the people who entered the Filecoin ICO.
If you want IPFS to be a replacement technology for the web, you need dynamic content. Else, it's a useful static content distribution network, but it's not "the web", not even in the sense of what the web was in the 90s, or the "web" any more than Bittorrent is.
Now, obviously, they're under no obligation to deliver anything. But I'm trying to understand what you mean when you say:
The vision of a IPFS-powered web working is beautiful
Only handling the static part of webhosting is something, but it's not everything.
I'm under the impression that the original comment was referring to an IPFS-powered web, rather than the web being powered by IPFS. Good ol' HTTP servers will continue to form the web as we know it, and IPFS can provide a new web of static content.
So at best IPFS is a replacement for something like S3? If I want to create an application, I can have the static content portion of it hosted on IPFS, but the brunt still on my own servers? That’s a very niche use case, I would say. And while it allows me to host my copy of the anarchist’s cookbook, it’s not going to be good for much else.
I didn't say it's everything. I don't think HTTP must die or will die. HTTP is great, it's awesome, wonderful. I would like IPFS to exist along with HTTP, that's what I said.
Actually, I think the fact that IPFS developers are trying to replace HTTP one of the reasons they fail so awfully in producing a good IPFS for static content. They try to integrate much more stuff than actually needed in the protocol.
I don't want to hijack the discussion from IPFS, but Swarm has good ideas with respect to dynamic content if you're interested how that might work in a decentralized setting, for example see Swarm Feeds presented here: https://www.youtube.com/watch?v=92PtA5vRMl8
I would love to see all these problems solved and IPFS working very well in the next few years, but I'm afraid the IPFS people are very good in making press releases and presentations, but not in delivering really good software as they say they do.
Anyway, they have no obligation to deliver anything to anyone -- except maybe the people who entered the Filecoin ICO.