You call it "lack of ambition", implying a certain arrogance; more humble people might just call it "a different sweet spot" of AI integration. After all, the goal in the end is not to use up as many AI tokens as possible, but the goal is to implement/perform a certain business case in the best way possible with regard to cost/speed/quality.
It's not like everyone using AI has the same software development cycle. It's not even that everyone using AI is developing software.
A harness of limited capability is a component that doesn't exist in your proposal, right? Just like non-automatable or at least hard-to-automate things like physical actions to be performed in the real world as part of a business task do not exist, too? Same goes for coordination with other real humans - doesn't exist.
Why don't you give some examples of tasks that you think fall into this category, where AI assistance only is the perfect solution and which could not conceivable be done more effectively autonomously by more capable models?
For coding, I don't see it.
Physical tasks? I don't know, it's not my area of expertise. I do not think AI is widely deployed for physical tasks yet, not even the SOTA is good enough.
China is actively tripping the US up by pushing the open-weight strategy, which is kind of smart. They realized that they obviously will not be able to make Western companies trust Chinese companies enough to just use proprietary models by sending all their data to services hosted by Chinese companies. The US is still able to attract this trust, although it's eroding quickly in spite of recent political events and the current trust is more or less a function of old habits that need some time to change. But China correctly found that - due to there being no old habits to piggyback on - they wouldn't ever be able to compete in this way, even if they had proprietary foundation models superior to their US counterparts, so they decided to throw sticks into the spokes of the US frontier labs by releasing top open-weight models worth billions of dollars in training cost and thereby devaluing the huge proprietary investments of the US labs.
Their ‘open weight strategy’ was invented, to Chinas surprise, by the Western press after the DeepSeek event. Of course all the actual systems like Baidu, Bytedance are closed weight and basically all anyone uses. Meanwhile the advanced system are crossing security frontiers: soon only inferior models will be ‘open’ (as with OpenAI, even) the rest closed. — Or where open weighted, they will be impossible to run without a private data center, come with absurd ‘security scrutiny’ licenses like GLM is starting — or licensing requiring a cut, as with Kimi, which is basically a scheme to get western companies to do buildout for them
Ehm, sorry, but no, this is not how lithography works. You cannot "hide" functionality in circuitry your machines are producing if your machines' job is to shine light through a mask.
You'd have to be the producer of the machine producing the mask. Or, even better, the software that produces the plan according to which a machine produces a mask.
I didn't say to hide it. My suggestion is to create international AI safety rules which companies must be in compliance with if they want to buy and service ASML machines.
Well, then Samsung Electronics appears to be dumb for leading this investment round? They probably only do it because they're European...oh, wait...
> so if you don't have the most intelligent or cheapest model in the world, you're losing
So how does this match up to the fact that there is currently OpenAI and Anthropic, both raking in money? They can't both have the smartest model at the same time, can they? And all those inference companies selling API access to open weight models on OpenRouter, which are apparently also earning billions already? While the former are probably bound to have much higher cost for research and training than they are currently earning, which may be called "losing", the latter don't have that problem, they can simply price their API access such that the money earned covers their costs, no training and practically no research necessary. In your theory these companies shouldn't have a cent of earnings.
> So how does this match up to the fact that there is currently OpenAI and Anthropic, both raking in money? They can't both have the smartest model at the same time, can they?
They are simultaneously first: the two leapfrog each other with regularity, and are meaningfully ahead of the competition.
Samsung is now essentially tied for being the world's most profitable company with Nvidia ($62b operating profit last quarter, vs $63b for Nvidia). They're drowning in cash. They're doing the same thing Nvidia has been doing: distributing the money to their business partners, to try to drive business growth faster (and or to keep it all propped up).
OpenAI and Anthropic are so close on benchmarks and release date that they are essentially ex-aequo at this point. The market is just hedging their bets.
There is no close second, because the AA Index points are expentially harder to get as you get closer to the first.
The value of these companies is not defined entirely by the state of their current models. A much more important signal is their chance of having the best model in the future. Just like with anything having to do with investment, this is the castle in the sky. Also, shame on me for simplifying things so much - but I still believe in my original sentiment.
Replce "best" with "most fit for purpose" and you're right. The future won't be a one size fits all kind of deal because hardware availability constraints will eventually punish oversized models even more.
I think that there's a real second mover advantage in letting others waste money on researching ultra oversized models while creating smaller and cheaper models from their learnings.
Yep, most wealth is ultimately dependent on some kind of ability to scrape off tiny bits of practical accomplishments of value achieved by large numbers of people. In some cases, such as your housing example, this is a very direct dependency. In other cases the dependency is indirect and less visible.
The smarter ones among the rich have realized this and are open for something like a universal basic income precisely for that reason: to protect their wealth and the position in the food chain this wealth affords them.
UBI will never happen. I don’t understand why it’s even brought up anymore. Social security isn’t even solvent, health care is a disaster, and people still trumpet UBI like all of the enormous glaring funding holes don’t exist.
Why are you correct even though the early Marxists (who posited that capitalism would inevitably lead to socialism) were wrong? We have had mass production for a hundred years without any hint of socialism.
And I would like you to be right, by the way. But why should I believe you?
Doesn’t most of the developed world already have various forms of socialism? The U.S. is an outlier here, which is due a number of factors unique to this country.
Fair, but as an American I’m still interested in this more
limited question. Why were the early American Marxists wrong and why are the new Americans saying similar things right this time?
There will be a form of UBI, because of the need for it, eventually. It will probably never be a 'fair' system (there probly will still be 1000xUBI people) but it will be necessary to prevent a lot of problems.
Think of it this way. The percentage of the population that will not have enough skills, 'smartness' and or knowledge to serve the community in a profitable way, increases over time. Today the group includes mostly the very young, the elderly (which in a way already have a 'kind of UBI', but not the complete lifespan) and people with a severe illness. Tomorrow new groups of people will be included, like people who stopped going to school at 17,18yo or so, and so on.
Suppose society provides those people with only the very minimal money to survive and no entertainment, traveling, proper housing, life choices etc. In that case not only those people, but the society as a whole will suffer because of unrest, riots etc. At a certain point in time, UBI can easily paid for by the wealth that automation will bring. Today probably as well, but the pressure of unevenly spread wealth is still able to keep it from happening, rich people still need enough poor people to work for them directly (house/boat personnel) or indirectly (mine coffee, chocolate, soy, battery minerals, ...)
Why are you so sure UBI is the most efficient solution to those problems? Another solution is for the wealthy to let the poor live miserable lives and to use technology to oppress them. A protest can be put down with drones, robots, and chatbots.
We have state supported pension plans in most developed countries, unemplyment insurance, these large welfare states with extensive public education, national health and so on, so while the means of production mostly haven't been socialized, the fruits often have, through taxation. Now, some of this existed before the Industrial Revolution -- I wasn't aware how much until I read Karl Polanyi's The Great Transformation, which is a more important book now than ever, I humbly propose, but the scale is dwarfed by what we have now. And as Polanyi points out, we did get socialism as a response, as well as fascism, which was often btw called corporatism (as in the nation as a single body, not having to do with companies). Liberal democratic capitalism won out, for a while, and in large part because it became social democracy, or so goes a claim to which I subscribe. Without the social welfare aspects of modern democracy, the system would likely have broken politically.
Anyone who thinks wealthy people willing part with any amount of wealth en masse hasn't studied history.
One of the reason democracy has tended to be a stable form of government is that it naturally finds a balance between the haves and the have nots -- the boundary where the haves are comfortable parting with that much to live in a stable society where they keep the remainder, and the have nots are afforded some amount of social services for their most accute needs.
That's all predicated on a "or riots / internal military action" alternative though.
We've lived through a pretty stable post-WWII economic bargain period, and historically there's not a ton of certainty that continues through distributive renegotiations, which tend to be bloody.
UBI money needs to come from somewhere. Hence it will and can never happen. Fake money helps nobody. There is no difference between getting 0, 1000 or 10000 fake dollars a month if they value of the dollar will go to zero
This frustrates me so much. Where is the money coming from? The middle class _is_ the economy, if they all decide to say “fuck it, UBI is enough” or can’t get a job, who the hell is funding UBI? This is an enormous hole in the UBI discussion that’s just completely ignored.
Again, we can’t even keep social security solvent, which is basically UBI for old people. It won’t work, the math doesn’t math, and everyone who wants UBI to be a thing just completely ignores this fact.
In a world where both creation and consumption is by humans, the productivity needs to align with consumption.
Arguably, that is a century since that was the case, so we tax extra productive human beings in order to make sure that everybody can consume.
This trend need to be accelerated as productivity accelerates.
Ubi, negative tax, etc. There are many good ideas on how to fix it.
However,if this discussion annoys you, I would strongly recommend you to learn more about the subject as it is indicative that you have some holes in your knowledge.
The money is just a gauge of how much food, housing, clothing, energy,... one person can consume versus another. Money is not absolute, it is relative x/y. Ultimately, the real stuff can be produced by machines operated by say 10 percent of the world population. Machines or robots or even AI can pay taxes, their owner hands over xx percent of the income produced by it to the government who gives it as eg ubi to people.
Profitable companies. This is incredibly obvious. It is where dividends come from already.
You keep mentioning social security but it isn't comparable as it has a relatively low income cap on payroll taxes and raising this easily makes it solvent.
What is actually frustrating is the wealth of the richest 400 people in the US now equals 20% of GDP. In 1982 it was only 2%. THE MONEY IS THERE!
It’s not. It’s really not. I’m sure you’re familiar with people borrowing against their wealth to avoid taxes. That’s where this fictional money exists.
You don't seem to know what dividends are. Dividends are x dollars for every share you own that the company gives you that come from the company profits. As a worked example Larry Ellison owns 1.16 billion shares of Oracle.
Oracle has paid a total of $1.50 per share in dividends so far in 2026. That is $1.74 billion of liquid cash flowing into Ellison's pocket while Oracle fires tens of thousands of people.
Please stop talking if you don't understand what you are talking about.
OpenRouters moat is that a) everyone knows it, but not their gazillion competitors, and b) their API URLs and key are already configured in your OpenCode/Oh-my-Pi/whatever harness or agent you use.
As long as they offer stable services and do charge the same API prices as competitors (or even less maybe, since they have the most inference providers on board, because OpenRouters' prime popularity also exists with inference providers) you do not really have an incentive to go through the hassle of changing all your configurations.
What you just wrote isn't a moat at all. One is marketing, the other is a find/replace.
A "moat" is something that protects your product that is really hard to overcome. Like a migrating your database to another vendor, for instance... Or finding your friends and the people you follow on another social media service.
And you do not have flat priced quota for Fable 5, right? Because nobody has, as far as I know. So you'll probably not route any task to the "current best available SOTA".
Also: quota. Implies you do not have unlimited access even for flat prices. Which in turn implies that as soon as you hit the quota on the most expensive flat price plan, even you will suddenly discover the magic of economically sensible behavior.
OpenRouter is basically a payment system for LLM tokens. Yes, it does route TCP connections from you to an inference providers' cloud, too, but what is way more important is that it routes money from your wallet to inference providers'wallets.
The latter is the core business of Stripe. For them, buying OpenRouter to become the premier channel for LLM token money makes perfect sense. At least if you assume that the current state of labs offering heavily subsidized subscriptions directly is only temporary and the future lies in people buying tokens and switching between models fluidly - and I consider that the future, in light of the recent developments with Kimi K3.
I had assumed they’re just reselling inference, where they’re “routing money” the way Walmart is “routing money” from my wallet to whoever makes Cheez-Its.
Are they doing something unique from resellers there?
They are reselling inference. That is not a novel concept, indeed, a stationary merchant like Walmart does conceptually the same. Although since inference doesn't require any stockkeeping, I would rather compare it to Amazon Marketplace.
But it's been novel for inference services when OpenRouter was founded. And nowadays they have a considerable foothold in the market. There are competitors, but the one everyone knows is OpenRouter.
And since they do not need to maintain any stock, don't need to do anything with queries but route them through 1:1, the most complex thing they do from a business perspective is that they collect your money and route the right amounts to various inference providers that served you.
They are simply out of ideas to keep the most expensive party in the history of mankind going.
That's it. Simple as that. When you grasp for straws in panic mode, you don't exactly spend time strategizing and weighing the pros and cons of each straw carefully.
It's funny that you can legitimately just add " - OMG!" in the slang acronym meaning after any of its creations' names.
reply