1. Yes, but if i can't rely on openrouter to route to providers to give me the best price and the best uptime across a number of providers, and it instead gives me inconsistent results, then I will not use them.
2. As long as the apis use the openai spec, it should be fine? And what makes you say the providers are using different weights? The blogpost says the exact opposite?
3. Great example, if amazon does not lead me to good products, I will stop using it, and this is why I dislike amazon. There are so many crap products, and the search seems to try to push crap products instead of what i'm actually looking for at a good price.
You take a bunch of providers with not great uptime, put them in a pool and now you get great uptime - but it doesn't work if it's at the cost of shitty performance or failing toolcalls.
> 1. Yes, but if i can't rely on openrouter to route to providers to give me the best price and the best uptime across a number of providers, and it instead gives me inconsistent results, then I will not use them.
OpenRouter does reliably route to your specified model and provider, otherwise it'd pretty much be fully broken. Parent is complaining about the auto-provider chosing, not that all providers are unreliable.
> 2. As long as the apis use the openai spec, it should be fine? And what makes you say the providers are using different weights? The blogpost says the exact opposite?
In theory, yes. In practice, no, there are differences. Ollama, llama.cpp, vLLM and SGLang all say "ChatCompletionRequest" compatible, but the devil is in the details, they don't have 100% the same request/response schema across all compatible models.
> 3. Great example, if amazon does not lead me to good products, I will stop using it, and this is why I dislike amazon. There are so many crap products, and the search seems to try to push crap products instead of what i'm actually looking for at a good price.
Yup, makes sense! If you're unable to find models when you use OpenRouter, it makes zero sense to continue to use OpenRouter.
> You take a bunch of providers with not great uptime, put them in a pool and now you get great uptime
Huh? That's not how it works or does it make sense, nor have I've seen anyone use OpenRouter like that.
Doesnt have to be all providers being bad, any unreliable providers still being routed to causes big issues.
2. Not saying they dont solve a problem, but if we can't rely on the providers being routed to, i don't really care if they provide a really nice api..
3. We are not talking about models, we are talking about providers of models. Openrouter does not route to models, it routes to providers.
What do you mean? Are you saying openrouter will not route to a provider that is up, versus one that is currently down?
> Parent is complaining about the auto-provider chosing, not that all providers are unreliable.
Parent is claiming that the choosing is unreliable. If I rely on a provider to bring me tuna to some spec, but they get it from many different fishermen, it doesn't mean that the tuna doesn't have meet the spec. The complaint is that they're given a bunch of knobs that simply don't work with providers that they could be switched to. That's like saying that I want my tunas to be 20lbs. minimum, and I get switched to a provider that doesn't weigh their tuna at all.
The choosing is all OpenRouter provides. If it doesn't do that, then what is it good for? If I have to permanently pin the one provider who doesn't ignore what I've asked, why shouldn't I just deal with them directly?
edit: it's really supposed to reduce providers to a commodity market. If you're selling e.g. produce to a commodity market, you can't just ship whatever the hell you want. You ship something indistinguishable from others, or more likely the market itself allows you to grade what you're shipping so it's put into a bin with virtually identical stuff. The customer just buys Grade B Wheat.
Specifically for a terminal, i'd really prefer it to be open source.
Primarily for security reasons, but also just so it's easier to avoid slop, in times like this with heavy LLM usage.
Yes, there is a lot to unpack - and im sure very smart people has worked on these changes, so spotting what is and what is not peculiar ways to get around EU regulations is not easy.
Valve is not literally the first but they played a big part in normalizing both lootboxes and micro transactions. Don't rewrite history just because you are a fan.
Not to mention their role in you not owning your games.
> Not to mention their role in you not owning your games.
I do use Steam to "purchase" games, and it irks me that they're still allowed to show "Buy" when in reality you're essentially leasing/renting the game, can't believe it's legal for them (and others) to trick people like this still.
A Steam purchase I have more confidence in than a physical game copy to survive. I trust Steam to honor its agreement with me more than I trust in myself and my feline overlords to keep a game CD alive.
In a previous timeline, this has led to me going on ebay to find CDs of a long lost game (EarthSiege 2), which I promptly uploaded to the Internet Archive as the one distributed by the current license-holder at the time had an older, unstable version with bugs and, more importantly, no audio and my own original copy got damaged to hell and beyond...
Sure, I agree with all of those things, but the fact still stands, Steam is actively lying to customers as the store pages say "Buy" and "Purchase", not "Rent" or "Lease", which are more accurate. You don't actually own the product.
Don't get me wrong, as mentioned, I use Steam and like Steam/Valve, but that move is a bit shitty regardless.
How could it be confusing when that's actually what happens? Imagine HN showed "Delete comment" instead of "Reply" under the comment input, don't you agree that be misleading?
There is a product in the cart, which is a game, and the button says "Purchase", no where does it say anywhere that it's a license (although that's obvious), nor that I don't actually "own" this game after I "purchase" it.
Sure, minor detail perhaps, but I'd still argue that something Steam could do better, and since the industry is lacking self-regulation about this, I'd argue more regulations are needed for this even.
It's on the cart page, before you check out. And I do agree that it should be much more front-and-center, rather than the sort of fine-print thing they have now.
What? Valve basically invented making money with skins and lootboxes, it started with TF2 hats. There is an insane amount of money in the CS2 skin market.
It amazes me how productive it's possible to be using AI, but I also has this nagging feeling that we are being reeled into being so reliant on this that when the price starts going up, we will simply eat the cost.
The math is pretty simple, and it's easy to justify still paying the price even if it goes up 10 fold, when compared to hirering more resources its still cheap.
So I guess having multiple players and competition in the market is the key?
Going forward, models will start specializing. Anthropic will build a BioMed model for large drug companies. A math/compsci model for frontier theoretical research. A physics modelf or nuclear research. They can communicate each other for synergy effects e.g. for areas where math meets biomed etc. This will be cost reducing as well. We plebs don't need advanced models for our plumbing software work. Following example applied to AI capabilies will make it clear.
Does everyone need a graphing calculator?
Does everyone need a scientific calculator?
Does everyone need a normal calculator?
Does everyone need GeoGebra or Desmos ?
Do you know Zuckerberg well enough to be able to engage in an interesting conversation about his hypothetical behavior if he was a bartender?
Do you know Zuckerberg well enough to be able to engage in an interesting conversation about whether or not he would continue to grant a specific person access to filters, knowing that they're harming that specific person?
I guess not. Speculating about it seems pointless at best.
I've been working with physics engine (cannon then rapier) + three js recently using Claude and found that AI was struggling quite when it came to fine tuning physics constants (friction, weights etc.) quite a lot. A human touch was needed - ended up vibe coding a small debug / admin panel where I could adjust those manually.
2. As long as the apis use the openai spec, it should be fine? And what makes you say the providers are using different weights? The blogpost says the exact opposite?
3. Great example, if amazon does not lead me to good products, I will stop using it, and this is why I dislike amazon. There are so many crap products, and the search seems to try to push crap products instead of what i'm actually looking for at a good price.
You take a bunch of providers with not great uptime, put them in a pool and now you get great uptime - but it doesn't work if it's at the cost of shitty performance or failing toolcalls.
reply