I always thought Accept (and Accept-Language) headers are quite neat. Surely I can try article.es.md first, get a 404, try article.en.md, get a 404, try article.es.txt, article.en.html and so on, until I find the thing I'm looking for. But Accept let's me say "I'll take any one of these, preferably in this order". This is especially useful now when agents are reading the web and they don't really need all of our HTML code - just the text.
If you're versioning the whole API though, I agree it's best behind a a /v2/ prefix.
It's interesting — "knowing how to search" used to be a skill. One wouldn't search for "How did Cantor come up with his diagonal proof?", but rather "cantor diagonal proof origin". You would see "normies" searching and wanted to bang your head against the wall seeing them searching like they're talking.
But seems like they won? Why know how to search when you can simply ask your question. You can even tyipe it layke dat and it would still work.
This is under-appreciated part of it. Search had been deliberately degraded for some time now as part of the usual enshittification arc. Where as AI is still in the early part of the arc where its trying to do better, so the difference between them seems even bigger.
But seeing disney+ now go all ads for all tiers just shows that's the way they arc bends. Eventually AI will take over and when it does, it will then turn into the shittiest shit ad-infused service the world has ever known.
> This is under-appreciated part of it. Search had been deliberately degraded for some time now as part of the usual enshittification arc. Where as AI is still in the early part of the arc where its trying to do better, so the difference between them seems even bigger.
That's how AI will surpass us. Once we enshittify humans sufficiently, AI will flourish. That's why I support extensive AI use in school classrooms, the younger the better, it's the best policy for OpenAI and Anthropic investors.
I would argue this was always a bit silly, and mostly due to UI shortcomings of search platforms. The fact you needed to add "magic" params to shape the results speaks volumes.
Any UI that fundamentally tries to reshape how you are expect to interact, or impose certain "behavior" is wrong. This is also why we are using touch instead of a stylus.
AI won because they took the paradigm of presenting a new way of doing something in a familiar way. An LLM works very similarly how you would ask a knowledgeable friend, and google worked similarly how an engineer would query a database.
Phrasing it as a UI shortcoming is underselling it. The search mechanism itself was dumb[1] and therefore the user had to be more intelligent. As an example, knowing synonyms for what you were searching for, in order to disambiguate the query from a more popular term that would likely dominate the results but was irrelevant for you, was a major skill.
[1] Yes, we can argue that LLMs are dumb, also. But they magically do "get" your intent with your prompt, unlike the search engines of yesteryear.
Nothing has changed, though. In my office the ones that have really boosted productivity are the ones putting in the effort to craft solid prompts and understand when to move that slider on reasoning effort and model selection. Or understand and put thought into how to leverage the tool, like project folders with the context to all or part of your job the model can reference. Everyone else throws a lazy prompt at the default 'instant' model, gets a crap response and then they give up.
You're absolutely wrong if you think those people are managing to get an answer first try now. People's searches remain frequently incoherent. There's a reason Google's AI results frequently end with some text asking for clarification, or guessing what you actually want to do.
Finding the right words to please the currently popular search engine is not a skill that easily translate elsewhere. It is not like programming where precision is key, searching has always been a bit fuzzy. Fact checking, crossing information, understanding primary sources, etc... these are real skills, typing words in a search engine is meh.
That we now have language models that allow let machines capture the intent of the query without the need for special incantations is a clear win to me.
Where LLMs are really excellent compared to search engines is when you don't really know what you want. You don't need to know about "Cantor diagonal proof", you just need to know "That math thing where you trace a diagonal across decimal numbers", and the LLM will immediately tell you about Cantor.
"knowing how to search" became useless when Google almost exclusively started returning SEO garbage. There was no longer any way to know how to search.
I'm surprised google didn't return stuff about Cantor-Fitzgerald losing hundreds of employees on 9/11, considering it's the 25th anniversary.
I remember wanting to look up something about the Andrew Niccol/Nicolas Cage movie "Lord of War", during the time the game "God of War" was getting all the hype. Guess which word Google assumed I got wrong, and what all the results were all about.
And it was more difficult, too. You had to make critical decisions while you were working to gather the information you were after. The work had beneficial side effects.
But it also took longer. And free search got shittier. Tradeoffs.
Note sure what you mean by "tools". It does support function calling, so you can hook it to whatever tools you want. I'm using it with Home Assistant to control my smart home devices.
It sounds like your criticism is about their product, not about their business model.
The business model of having a popular product with great documentation, which leads free users to additional paid services, seems like a very valid business model.
Even the criticism you have for their product is along the lines of "the product only worked because they identified a problem in the market; If someone else identified it, this product wouldn't even be needed!". Which is, well, true, but also true for almost any other successful product.
I got a kobo clara bw and a xteink x4 that I gave to my kid. Im quite happy with the kobo, it’s a much better experience for reading imo despite not having buttons. The touch screen is usable after all. I started dumping things into epub format, for example lyrics/chords, things that I want to read, etc. chatgpt is quite helpful with formatting epub files.
I considered buying an X4 for the portability (and to be honest installing and tinkering with crosspoint sounds fun).
But the kobo can fit in my jeans pocket and is about the size of a normal paperback page. I feel like the X4 would be too small and might be frustrating.
Yeah, the connector they've made is absolutely bananas, wonder what they were thinking? Was there a 3rd-party docking ecosystem they were expecting to be spawned by this, or something? The magnetic connector by itself makes no sense, unless I severely misunderstand how it's supposed to be used in practice.
Just for improved thinnness; they're able to reduce about 2 mm from the thickness with the pins (and you can still technically use them for data transfer depending on how it's wired to the SoC).
In the video he explains that the goal of the hybrid system is mainly to be used when for some unexpected reason the airplane cannot land at its original destination.
If you're versioning the whole API though, I agree it's best behind a a /v2/ prefix.
reply