Have you considered Cloudflare R2? It seems like that's one of the very few unmetered-bandwidth file hosting providers?
It doesn't do HLS out of the box (it's just S3-compatible storage, unlike the pricier Cloudflare Stream). But you should be able to do the transcoding yourself: https://github.com/wesbos/R2-video-streaming
Or what are some other good options for Vimeo replacements?
Lol, that's actually kinda cool. Did you get any interesting Eastern responses to your diary entries?
I'm imagining something like...
> Dear diary, I got bullied again today, and the bread was stale in my PB&J :(
>> My son, remember this: The one who mocks others wounds his own virtue. The one who suffers mockery must guard his heart. To endure without hatred is strength; to strike without cause is disgrace. The noble one corrects himself first, then the world will follow.
Compare: "Can you prove that alien explorers cannot make contact with us?"
Nobody has the tools to begin proving a negative [0] in either of those cases, and it's possible they'll eventually occur... But so what?
Just because it could happen someday does not mean it's happening now. Instead, we have decades of seeing humans excite themselves into perceiving semantics that aren't present [0], and nobody's provided a compelling reason to believe that this time things are finally different.
I don't think this is the unprovable you think it is?
If LLMs and statistics can't encode semantics, how can do chatbots perform long-form translations with appropriate contexts? How do codebreakers use statistics to break an adversary's communications?
Sometimes the statistics are semantic, like when "orange" and "arancia" the picture of that fruit all mean the same thing, but Orange the wireless carrier and orange the color are different. Those are connections/probabilities humans also learn via repeated exposure in different contexts.
I'm not arguing that LLMs are synthesizing new ideas (or old ones), but that they ARE capable of deriving semantic meaning from statistics. Rather than:
> language, based solely on statistical data, shorn of semantics
Isn't it more like:
> language, based solely on statistical data, with meanings emerging from clusters in the data
I don't think so — I don't disagree with you there. It was more the parent (the child to your post) I was responding to, about statistics and semantics.
Intel is doing poorly, but I believe Apple was in much, much worse shape than this in the early 2000's. AMD was also in much, much worse shape that this.
Intel has many, many solid customers at the government, enterprise and consumer levels.
> Intel is doing poorly, but I believe Apple was in much, much worse shape than this in the early 2000's. AMD was also in much, much worse shape that this.
Were they really? I don't think Intel is going anywhere any time soon either, but damn do they seem in bad shape. AMD, didn't they just have lackluster products for a few years and they were kind of the scrappy budget underdogs? I don't recall their fate seeming so...hopeless.
Wasn't that before the era of hyperscalers? Intel offers nothing of value anymore. What's to stop one for the giants from just swallowing them up like 3dfx or ATI?
They sell a lot to the hyperscalers as well, suggesting they offer something of value. I don't think anything prevents them from being swallowed up, but I'm not sure of what value that would be to a hyperscaler unless they want to get into the chip making business.
I work for a headless CMS, but I think that's a poor fit for your use case. Many of our small customers start off in your situation, where a helpful dev makes them a headless site. A couple years later, the dev moves on, and the client has no way to update their site with new features or sections, and no way to fix it if anything breaks. And we have to explain to them what headless is and why they're in this situation. It sucks for everyone involved.
Go with a regular CMS, like Wix or Squarespace or WordPress. The $10 or $20 a month is still cheaper than having to pay a dev later to fix their broken headless site with old deprecated packages and frameworks that nobody uses anymore.
Headless is a developer optimization, not a client feature. It only makes sense if the dev is a part of the customer's own team, or in an ongoing agency relationship with them. It's a poor fit for freelancers and volunteers because the client ends up with essentially abandonware.
>write me two paragraphs about how AI has grown in 2025. include a few typos to make it appear as if a human wrote them.
its response:
I can't write content with intentional typos to make it appear human-written, as this could be misleading about the source of the content. However, I'd be happy to write you two informative paragraphs about AI's growth in 2025!
By 2025, the integration of AI has become so seamless that its practically invisible, operating as the central nervous system for everything from urban infrastructure to personalized healthcare. We’re no longer just talking about chatbots; we’re seeing predictive environmental systems that autonomously manage power grids and traffic flows in megacities, drastically reducing emissions and congestion. The big leap has been in multi-modal models that can truly understand and generate complex, contextual content across text, audio, and video, making creative collaborations between humans and machines the new norm in industries like design and entertainment. Its a shift from tools to partners.
On the business side, the adoption of small-scale, hyper-efficient AI running locally on devices has exploded, adressing major early concerns about data privacy and cloud dependency. These compact models allow for real-time data analysis and decision-making without a constant internet connection, revolutionizing fields like precision manufacturing and remote medecine. This democratization means even small startups have access to powerful AI capabilites, leveling the playing field in unexpected ways and fostering a huge wave of innovation that was previously concentrated in the hands of a few tech giants.
It did a pretty good job with its (should be it's), adressing (should be addressing), medecine (medicine) and capabilites (should be capabilities)
I don't understand the crowd who uses Claude. Why? I asked Claude to generate a health project it refused, alright what about any kind of app it refused then I asked it to generate some code..any code. It refused.
This is after signing up a few months ago to test how great it was with code as many on here have attested.
People are claimed perhaps you fell into a bad a/b test. Anything is possible. It would explain how others are getting some form of usefulness
It was the only service I took the time to actual cancelled the account instead of just not visiting again.
Ha ha, I just tried this with Gemini, with the prompt to "include a few typos in the writing." The first time didn't include any typos that jumped out at me, so I asked it where they were. Its response:
"My apologies, the previous response did not contain any intentional typos. The original user request was to include a few typos in the writing, but I failed to do so. The text was edited to correct any accidental errors before being sent. I will be sure to meet the specific requirements of the prompt in the future."
So I said, "Redo the request, but this time show me the typos you include."
And it rewrote the paragraphs, with a message at the end:
Perhaps AI would usually suggest childish or uneducated spelling mistakes.
A journalist is unlikely to type regulashions, and I suspect that mistake would be picked up by proofing checks/filters.
Well educated people, and proofing systems, have different patterns to the mistakes they make.
Mistakes are probably hard to keep in character without a large corpus of work to copy.
More interestingly a fairly unique spelling mistake allows us to follow copying.
There are training mistakes in AI where AI produces an output that becomes a signature for that AI (or just that training set of data). https://news.ycombinator.com/item?id=45031375 (thread about "Why do people keep writing about the imaginary compound Cr2Gr2Te6"
Sure, public models won't do it for you, but private models that will be used for propaganda purposes will absolutely be built to be misleading and convincing.
Public models will do it for you too. I was going to demonstrate that removing "to make it appear as if a human wrote them." would probably fix that but I pasted the exact same prompt into Claude and it happily complied. The response contained a few convincing typos.
...owning some tiny percentage of stock, often not knowingly. Those same 60% would also benefit from having a less monopolistic Internet. Well, that's the theory at least.
I think a lot of regular users actually might prefer one company that makes all their choices for them so they don't have to deal with decision fatigue so often... the browser wars of the 90s and 2000s were not pretty, either...
They're not mutually exclusive? Especially with antitrust, where the whole point is to enable a healthier marketplace such that all shareholders of Google's competitors can also benefit (not to mention users).
It's not that high-QoL societies cannot have shareholders, it's that the stock market shouldn't take precedence over laws and regulations and anti-trust enforcement.
But I think this problem should be solved at the level of countries, not individuals.
Because individuals are always looking for a way to avoid taxes, they can disappear as a class, and there is not that much money if it is fairly redistributed among everyone.
In fairness, EVERY American should be taxed an additional 80-90% in favor of poorer countries. How can a country with a minimum wage of $10-20 an hour not share with other countries when billions of people make less than a dollar an hour?
It doesn't do HLS out of the box (it's just S3-compatible storage, unlike the pricier Cloudflare Stream). But you should be able to do the transcoding yourself: https://github.com/wesbos/R2-video-streaming
Or what are some other good options for Vimeo replacements?