HN is mostly a place where technologists gather, not corporate heads of IT or other business people. This is especially true of the subset of users who actively participate rather than only reading.
And it is not unusual in the least for an enterprise product to be wildly profitable but not admired by technologists. Indeed, it's the default; Oracle, SAP, Microsoft, etc.
What is interesting is to look for examples of things that break this mold, that are both profitable and mostly admired. Frankly, I can't think of any... All the ones I can think of were out-competed and either acquired and ruined or just run out of business. Maybe RedHat is the closest example... I'm not sure though.
What's interesting is the substance of the complaints of those products. Most of the comments are complaining that Splunk is expensive, but no comments I've seen are complaining that it doesn't work or do as advertised. Same for Oracle DB. It's ungodly expensive, and there are (many) other options out there, but you don't really see complaints that it's not able to perform (after an expensive consultant has had a go at your companies checkbook). The Fedex and Paypals of the world can afford to pay for Cisco/Splunk and Oracle licenses.
What's interesting is things that break this mold, like Microsoft Teams, because that's something that can be disrupted, and thus be successful, by having a better product.
F# is nice but seems like a fairly conventional functional language. My first reaction to some of the features of Koka (also MS) was I didn't know that was even possible.
Cloudflare's verify human challenge screen is so intrusive and frustrating that it will cost them their credibility IMHO, if it hasn't already. Some part of me feels that a properly designed cache should be able to handle any level of abusive traffic like a p2p cache would, and if it can't, then what are we all doing?
The problem is a cache needs cooperation with the backend for invalidation: Cloudflare’s robot check can apply to every page right before it talks to the backend at all
But I don't think there's really a great place to get a zeitgeist of the rest of the population. I think they're mostly doing other stuff rather than talking about technology on internet forums. (They're smarter than us.)
Actually yeah, closer than most. I think it's a somewhat grudging admiration at this point, increasingly so as they do more and more also-ran services.
But yeah, this does seem right for the "core" services; ec2, s3, maybe lambda, etc.
AWS business model is to just literally take a popular OSS system and provide it as a service.
It was like that from the beginning. That's why there's much less animosity towards AWS, because they just allow you to run your X without the overhead of infra investment.
That is something they do, which I strongly dislike, but it isn't their business model. Their business model is "pay us to run things on our infrastructure instead of building your own, with an option to be billed based on your usage".
The "take a popular OSS system and provide it as a service" thing is a complement to that business model, because they can say "now that you're using our infrastructure, you can also use all these services, and we'll manage it for you, and you'll only have a single vendor to pay". It provides additional value and lock-in to the business model, but isn't the essential part of it.
And no, that isn't where it began. Providing managed services for open source systems was not a part of their initial value proposition. When I started using EC2 (with EBS and S3), one of the tricky things was getting our own database infrastructure to work reliably on EC2.
It's true that RDS was released not long after, and did the "take a popular OSS system" thing, but they really didn't embrace that model until years later. Indeed, I think RDS still seems like second fiddle to their proprietary non-relational DB service.
Maybe in the beginning. Taking an OSS package, cloning its wire protocol, and then offering their closed source almost-compatible version without having to contribute anything back upstream earns them a lot of animosity.
HN is mostly a place where technologists gather, not corporate heads of IT or other business people. This is especially true of the subset of users who actively participate rather than only reading.
And it is not unusual in the least for an enterprise product to be wildly profitable but not admired by technologists. Indeed, it's the default; Oracle, SAP, Microsoft, etc.
What is interesting is to look for examples of things that break this mold, that are both profitable and mostly admired. Frankly, I can't think of any... All the ones I can think of were out-competed and either acquired and ruined or just run out of business. Maybe RedHat is the closest example... I'm not sure though.