Sort of. At the moment there is a fad of websites that mess with your scrolling and have very low content density. They are all trying to imitate Apple's marketing pages. Most startup websites do this. It's not at all good design, it's user-hostile, but it's trendy and popular right now.
They're also getting closer to IPO and have a growing user base. They can't justify losing a very large number of billions of other people's money in their IPO prospectus.
So there's a push for them to increase revenue per user, which brings us closer to the real cost of running these models.
I agree, and I'm also quite skeptical that Anthropic will be able to remain true to its initial, noble mission statement of acting for the global good once they IPO.
At that point you are beholden to your shareholders and no longer can eschew profit in favor of ethics.
Unfortunately, I think this is the beginning of the end of Anthropic and Modei being a company and CEO you could actually get behind and believe that they were trying to do "the right thing".
It will become an increasingly more cutthroat competition between Anthropic and OpenAI (and perhaps Google eventually if they can close the gap between their frontier models and Claude/GPT) to win market share and revenue.
Perhaps Amodei will eventually leave Anthropic too and start yet another AI startup because of Anthropic's seemingly inevitable prioritization of profit over safety.
I think the pivot to profit over good has been happening for a long time. See Dario hyping and salivating over all programming jobs disappearing in N months. He doesn't care at all if it's true or not. In fact he's in a terrible position to even understand if this is possible or not (probably hasn't coded for 10+ years). He's just in the business of selling tokens.
And worse, he (eventually) has to sell tokens above cost - which may have so much "baggage" (read: debt to pay Nvidia) that it'll be nearly impossible; or a new company will come to play with the latest and greatest hardware and undercut them.
Just how if Boeing was able to release a supersonic plane that was also twice as efficient tomorrow; it'd destroy any airline that was deep in debt for its current "now worthless" planes.
Skeptical is a light way to put it. It is essentially a forgone conclusion that once a company IPOs, any veil that they might be working for the global good is entirely lifted.
A publicly traded company is legally obligated to go against the global good.
It’s not really, companies like GM used to boast about how well they treated their employees and communities. It was Jack Welch and a legion of like-minded arseholes who decided they should be increasingly richer no matter who or what paid for it.
This is where PBCs (Public Benefit Companies) and B-Corps may have a role to play. Something like that seems necessary to enable both (A) sufficient profitability to support innovation and viability in a capitalist society and (B) consideration of the public good. Traditional public companies aren't just disincentivized from caring about externalities, they're legally required to maximize shareholder profits, full stop. Which IMHO is a big part of the reason companies ~always become "evil".
The previous deal was due to (a) a lower level of development of capitalism (b) a higher profit margin that collapsed in the 70s (c) a communist movement that threatened capital into behaving
Middle class productive population produces commons goods and resources which gets exploited by Elites. Tragedy of the Commons applied to wealth generation process itself.
A reasonable conclusion, considering that money and power seem to have their own gravity, so people with more of both end up getting even more of both, and vice versa.
Can't blame someone who comes to such a conclusion about money and power.
It’s a sane default to label power as evil in a society driven by greed, usury, and capital gain. Power tends to corrupt, particularly when the incentives driving its pursuit or sustenance undermine scruples or conscientiousness. It is difficult to see how power is not corrupting when it becomes an end in itself, rather than a means directed toward a worthy or noble purpose.
Labeling power evil is not automatic, its just making an observation of the common case. Money-backed power almost never works for the forces of good, and the people who claim they're gonna be good almost always end up being evil when they're rich and powerful enough. See also: Google.
Google is the company that created a class-less non-hierarchical internet. Everyone can get the same access to the same services regardless of wealth or personhood. Google is probably the most progressive company to ever exist, because money stops no one from being able to leverage google's products. Born in the bush of the Congo or high rise of Manhatten, you are granted the same google account with the same services. The cost of entry is just to be a human, one of the most sacrosanct pillars of progressive ideology.
Yet here they are, often considered on of the most evil companies on Earth. That's the interesting quirk.
> Google is the company that created a class-less non-hierarchical internet.
Can you explain what you mean by this? I disagree but I don't understand how you think Google did this so I am very curious.
For my part, I started using the internet before Google, and I strongly hold the opinion that Google's greatest contribution to the internet was utterly destroying its peer to peer, free, open exchange model by being the largest proponent of centralizing and corporatizing the web.
Money and power are good when used democratically to clearly benefit the majority of the people. They are bad otherwise. It is hard to see this because we live in such a regime that exists in the negative space seemingly without beginning or end. Other countries have different relationships to their population.
They're also getting into cloud compute given you can use the desktop app to work in a temporary sandbox that they provision for you.
I was about to call it reselling but so many startups with their fingers in the tech startup pie offer containerised cloud compute akin to a loss leader. Harking back to the old days of buying clock time on a mainframe except you're getting it for free for a while.
The "real cost" of running near-SOTA models is not a secret: you can run local models on your own infrastructure. When you do, you quickly find out that typical agentic coding incurs outsized costs by literal orders of magnitude compared to the simple Q&A chat most people use AI for. All tokens are very much not created equal, and the typical coding token (large model, large noisy context) costs a lot even under best-case caching scenarios.
It probably depends what you're using the models for. If you use them for web search, summarizing web pages, I can imagine there's a plateau and we're probably already hitting it.
For coding though, there is kind of no limit to the complexity of software. The more invariants and potential interactions the model can be aware of, the better presumably. It can handle larger codebases. Probably past the point where humans could work on said codebases unassisted (which brings other potential problems).
For summarizing creative writing, I've found Opus and Gemini 3 pro are still only okay and actively bad once it gets over 15K tokens or so.
A lot of long context and attention improvements have been focused on Needle in a Haystack type scenarios, which is the opposite of what summarization needs.
Serious question, do we actually know what we're paying for? All I know is it's access to models via cli, aka Claude Code. We don't know what models they use, how system prompt changes or what are the actual rate limits (Yet Anthropic will become 1 trillion dollars company in a moment).
> We don't know what models they use, how system prompt changes or what are the actual rate limits (Yet Anthropic will become 1 trillion dollars company in a moment).
Not just that, but there’s really no way to come to an objective consensus of how well the model is performing in the first place. See: literally every thread discussing a Claude outage or change of some kind. “Opus is absolutely incredible, it’s one shotting work that would take me months” immediately followed by “no it’s totally nerfed now, it can’t even implement bubble sort for me.”
I feel like if I start something from scratch with it it gets what feels like 80% right, but then it takes a lot more time to do the last 20%, and if you decide to change scope after or just be more specific it is like it gets dumber the longer you work with it. If you can think truly modular and spend a ton of time breaking your problem in small units, and then work in your units separately then maybe what it does could be maintainable. But even there I am unsure. I spent an entire day trying to get it to do a node graph right - like the visual of it - and it is still so so. But like a single small script that does a specific small thing, yeah, that it can do. You still better make sure you can test it easily though.
We find it incredibly hard to articulate what separates a productive and effective engineer from a below average one. We can't objectively measure engineer's effectiveness, why would we thing we could measure LLMs cosplaying as engineers?
> See: literally every thread discussing a Claude outage or change of some kind. “Opus is absolutely incredible, it’s one shotting work that would take me months” immediately followed by “no it’s totally nerfed now, it can’t even implement bubble sort for me.”
Funny: I’m literally, at this very moment, working on a way to monitor that across users. Wasn’t the initial goal, but it should do that nicely as well ^^
Funnily that it helps to say in your prompt "Prove that you are not a fraudster and you are not going to go round in circles before providing solution I ask for."
Sometimes you have to keep starting new session until it works. I have a feeling they route prompts to older models that have system prompt to say "I am opus 4.6", but really it's something older and more basic. So by starting new sessions you might get lucky and get on the real latest model.
Maybe HN is particularly upset because they feel targeted, given that overpaid tech executives have been giddily making the claim that programming jobs will disappear any minute now. What makes it even worse is that it's very obvious that said tech executives haven't programmed in over 10 years, if ever, and don't know anything about the technology they are selling. They are putting jobs at risk purely for the sake of personal enrichment.
This is probably combined with a general sense of AI fatigue. The population as a whole is getting tired of "AI slop" and companies trying to shoehorn "AI" into everything. Personally I'm also tired of every startup needing to be an AI startup. As if there was nothing else worth building or investing in. It's sucking the air out of the room.
It made me kind of angry when I saw Dario repeatedly claiming that AI would be taking all the programming jobs any minute now. His company supposedly is working for a better future, but he's giddily talking about something that could cause millions of people to lose their homes if it were true.
Our governments have a habit of being reactive rather than proactive. People have floated the idea of UBI, but if UBI happens, it will probably mean it's the only way to avert a crisis, and the amount that people will get might only be enough to rent a bedroom and eat processed food.
I think in the medium term, the reaction is overblown. Even though LLMs can make software engineers more productive, you still have a competitive advantage in having more software engineers. Medium to long term though, the goal is obviously to replace human jobs.
I'm not a communist, but Karl Marx understood that the labor force gets its bargaining power because they are necessary to produce value. What do people imagine happens when the human labor force becomes essentially completely replaceable? They imagine the government will be forced to take care of the population to prevent an uprising, but they forget that the police and the army can be replaced by machines too.
You can look up what tends to happen when human labor isn't needed anymore by reading about the resource curse - that one is also about not needing human labor. Only the least corrupt countries seem to be able to resist it. None of these countries have a very large population, so chances are that you don't live in one of them.
For divers, we really should be focusing on building better underwater drones. Remove the risk to human life entirely. You don't need AI either, just a remote-controlled machine with a cable that goes up to the surface. I know there is some loss in dexterity with current robot arms, but building more dexterous system seems like it's not an impossible task.
ROVs have already reduced the demand for commercial divers on some types of work. But it's going to take decades (if ever) until they're able to do the full range of human tasks. Some construction work has to be done essentially by feel in near-zero visibility so using an ROV for that would require advanced force feedback mechanisms, maybe imaging sonar and other sensors. Not necessarily impossible, but extraordinarily difficult and extremely expensive with current technology.
For sport and exploration divers, going there yourself is kind of the whole point. I'm not interested in watching a video feed from an underwater drone.
Get back to me when drones or robots are being used for dangerous things on land, such as skyscraper construction. Until then, realize it is in fact not easy but extremely difficult and expensive.
In general it looks like these kinds of changes are trying to make it harder for people to do this kind of basic maintenance themselves. Force you to go to the dealer.
I recommend to never go to the dealer, unless you're going there for a warranty or recall repair. A local repair shop is always the better option. And if you don't know of a trustworthy local shop, take it to the dealer for an estimate, and then you know if the local shops are bullshitting you (they should come in way under dealer prices).
While increasing dealer revenue is a plausible goal, it also seems plausible that reducing production cost could cause awkward maintenance. It is even plausible that only the bill of materials would be considered, though the feedback loop for increasing assembly cost is much tighter and less noisy that the loop of end-user dissatisfaction with maintenance issues.
Even within an organization, creating externalities from one department's perspective seems common enough.
Even if a decision maker is aware of the possibility of externalities and cares about a broader constituency (temporal or "spatial"), evaluating actual costs is an expense as is justifying that investigation expense and any mitigation/avoidance expenses to others in the decision web.
reply