$700k/dsy. That's $260 million per year. There are 360 million paid seats of MS360. So they'd have to raise their prices $0.73 per year to cover the cost. No one will notice.
The Response:
OpenAI, the organization behind the development of AI models like GPT-3, has a few strategies to generate revenue:
Licensing and Subscription Models: OpenAI can license its AI models and technologies to businesses, developers, and organizations for various applications. This could involve offering different pricing tiers based on usage, features, and support.
API Access: OpenAI can offer access to its AI models through APIs (Application Programming Interfaces). Developers and companies can integrate these APIs into their products, applications, or services, paying for the amount of usage.
Customized Solutions: OpenAI can collaborate with specific industries or companies to develop customized AI solutions tailored to their needs. These solutions can range from customer support bots to content creation tools.
Premium Features: OpenAI could offer advanced features, improved performance, or specialized functionality as part of premium packages, enticing users to upgrade their subscriptions.
Partnerships and Collaborations: OpenAI can collaborate with other tech companies, research institutions, or industries to jointly develop and commercialize AI applications.
Consulting and Services: OpenAI could provide consulting services, training, and expertise in AI technology to help organizations integrate AI into their operations effectively.
Training and Workshops: OpenAI can offer training programs, workshops, and educational resources to help individuals and businesses better understand and utilize AI.
Data Services: OpenAI can offer datasets, annotations, and data-related services to researchers, businesses, and developers working on machine learning projects.
Vertical-Specific Solutions: Developing AI solutions tailored for specific industries, such as healthcare, finance, or marketing, and offering them as industry-specific packages.
Community Contributions: OpenAI can build a community around its AI models and offer a platform for users to share and monetize their own creations, benefiting from the broader ecosystem.
It’s important to note that OpenAI’s approach to generating revenue will likely be influenced by factors such as market demand, ethical considerations, user feedback, and the evolving landscape of AI technologies and regulations. OpenAI aims to strike a balance between generating revenue and advancing its mission of ensuring AI benefits all of humanity.
Open AI died the moment Meta’s Llama model weights were replicated completely open source. The outcome is guaranteed. It does not matter how much better the enormous proprietary model can be, people will never be okay with the level of intrusive data mining required for OpenAI or Google’s business model. Personal AI tech must be open source and transparent with offline execution. AI is the framework of a new digital economy, not the product.
I don't think it's as much that the meta model was replicated as much as they fully open sourced it with a license for research and commercial use.
I actually think the market demand will be fairly small for fully offline AI. The largest potential customers might be government who require full offline hosting, and there is a small group of companies servicing that niche. But even government customers who require that their data is segmented are simply having enclaves setup by the big cloud platforms where they guarantee that inputed data isn't fed into the training process and doesn't leave the customer environment.
I fully support folks who sustain open source AI frameworks, but in terms of commercial customers that will drive industry trends with dollars, I expect there will be demand for hosted solutions that use proprietary models.
The courts aren't going to side with copyright holders. As much as the US loves its ridiculous copyright laws it loves profit and being on the bleeding edge of tech more. There is absolutely ZERO chance that the United States will let China, who does not care about IP, carry the keys to the AI kingdom
Yeah, I was about to say, 99% of people are either unaware or do not care. Don’t mistake Lemmy’s privacy opinions as representative of the general population.
High interest rates baby. I noted this was happening when people were complaining about lowered quality because they were using less resource intensive operations.
Too much is made of the shrinking user base. I’m sure they’ll come back with a vengeance come the start of the school year in the northern hemisphere.
Also, maybe a tool like this shouldn’t be privately funded? Most of the technology is based on university funded research we all paid for. mRNA vaccine research was similarly funded with public money in mostly universities, and now we have to pay some private company to sell it back to us. How is that efficient? AI should be common property.
If it’s made from all of us it should be free for all of us.
I’m fine with these researchers going out and scraping the social networks to train models, it’s incredibly advantageous to society in general. But it’s gotta be crystal clear transparency and it’s gotta be limitlessly free to all who want to.
It’s the only way that any of this won’t result in another massive boundary between the 1% and us pod living grunts. It’s already a devisively powerful technology when harnessed adversarially, that power is reduced when everyone has access to it as well.
If you look at how much they spend per day (poster quoted $700,000 daily but said unverified), how would it make any sense to provide the service for free? I won’t argue for/against releasing the model to the public, since honestly that argument can go both ways and I don’t think it would make much of a difference anyway except benefit their competitors (other massive companies).
However, let’s assume they did release it publicly, what use would that be for the smaller business/individual? Running these models takes some heavy and very expensive hardware. It’s not like buying a rack and building a computer, these models are huge. Realistically, they can’t provide that as a free service, they’d fail as a company almost immediately. Most businesses can’t afford to run these models themselves, the upfront and maintenance costs would obliterate them. Providing it as a service like they have been means they recoup some of the cost of running the models, while users can actually afford to use these models without needing to maintain the hardware themselves.
Less than a million dollars a day for everyone who wants to in the whole world to use AI right now? That’s peanuts. A single city bus costs $5-800k to buy. Even if costs goes up to several tens of million a day for access for the whole world that’s incredibly affordable.
It’s crazy that something so useful and so cheap to run can’t be sustained in the current system. This seems like an argument against a market based solution to AI.
Less than a million dollars a day for everyone who wants to in the whole world to use AI right now?
You’re ignoring the fact that the cost scales with usage. Increasing its availability will also increase the cost, hardware requirements (which can’t really scale since there’s a shortage), and environmental cost due to power usage.
Even if costs goes up to several tens of million a day for access for the whole world that’s incredibly affordable.
With how many people are already using AI, it’s frankly mind boggling that they’re only losing $700k a day.
You’re also ignoring the fact that costs don’t scale proportionally with usage. Infrastructure and labor can be amortized over a greater user base. And these services will get cheaper to run per capita as time goes on and technology improves.
Finally, there are positive economic externalities to public AI availability. Imagine the improvements to the economy, education and health if everyone in the world had free access to high quality AI in their native language, no matter how poor or how remote. Some things, like schools, roads and healthcare, are not ideally provisioned under a free market. AI is looking to be another.
Finally, there are positive economic externalities to public AI availability.
There are positive economic externalities to public everything availability. We don’t live in this kind of world though, someone will always try to claim a larger share due to human nature. That being said, I’m not really interested in arguing about the political feasibility (or lack thereof) of having every resource being public.
With how many people are already using AI, it’s frankly mind boggling that they’re only losing $700k a day.
There are significant throttles in place for people who are using LLMs (at least GPT-based ones), and there’s also a cost people pay to use these LLMs. Sure you can go use ChatGPT for free, but the APIs cost real money, they aren’t free to use. What you’re seeing is the money they lost after all the money they made as well.
You’re also ignoring the fact that costs don’t scale proportionally with usage. Infrastructure and labor can be amortized over a greater user base. And these services will get cheaper to run per capita as time goes on and technology improves.
I don’t disagree that the services will get cheaper and that costs don’t scale proportionally. You’re most likely right - generally speaking, that’s the case. What you’re missing though is that there is an extreme shortage of components. Scaling in this manner only works if you actually have the means to scale. As things stand, companies are struggling to get their hands on the GPUs needed for inference.
There are positive economic externalities to public everything availability. We don’t live in this kind of world though, someone will always try to claim a larger share due to human nature.
Saying “Things are inevitably bad because of human nature” is just very weird, since we obviously do have good policies and we try to solve other problems like crime and poverty. It sounds like you already agree that this is good policy? You’re just saying it’s not politically feasible? OK, sure, we probably don’t disagree then.
That being said, I’m not really interested in arguing about the political feasibility (or lack thereof) of having every resource being public.
I am obviously NOT arguing that every resource should be public. This discussion is about AI, which was publicly funded, trained on public data, and is backed by public research. This sleight of hand to make my position sound extreme is, frankly, intellectually dishonest.
there’s also a cost people pay to use these LLMs.
OK, keep the premium subscription going then.
What you’re missing though is that there is an extreme shortage of components.
There’s a shortage, but it’s not “extreme”. ChatGPT is running fine. I can use it anytime I want instantly. You’d be laughed out of the room if you told AI researchers that ChatGPT can’t scale because we’re running out of GPUS. You seem to be looking for reasons to be against this, but these reasons don’t make sense to me, especially since this particular problem would exist whether it’s publicly owned or privately owned.
We probably don’t here, but like I said I’m not really interested in discussing the political feasibility of it.
I am obviously NOT arguing that every resource should be public. This discussion is about AI, which was publicly funded, trained on public data, and is backed by public research. This sleight of hand to make my position sound extreme is, frankly, intellectually dishonest.
I don’t think I ever disagreed that the models themselves should be public, and there are already many publicly available models (although it would be nice if GPT-N were). What I disagree with is the service being free. The service costs a company real money and resources to maintain, just like any other service. If it were free, the only entity that could reasonably run the models is the government, but at this point we might as well also have the government run public git servers, public package registries, etc. Honestly, I’m not sure what impression you expected me to get, considering the claim that a privately run service using privately paid-for resources should be free to the public.
There’s a shortage, but it’s not “extreme”. ChatGPT is running fine. I can use it anytime I want instantly. You’d be laughed out of the room if you told AI researchers that ChatGPT can’t scale because we’re running out of GPUS.
Actually no, I work directly with AI researchers who regularly use LLMs and this is the exact impression I got from them.
According to the study, the chatbot’s responses have worsened despite OpenAI’s efforts to ship new features to the tool designed to improve its usability.
Not to mention the amount of money used to procure GPUs from companies like NVIDIA to ensure that things run seamlessly.
Aside from monetary issues, OpenAI is also experiencing a decline in the number of users that leverage its chatbot’s offerings.
OpenAI’s APIs have increasingly gained the interest of organizations initially opposed to the whole Artificial Intelligence idea and incorporating it into their workflows.
And while OpenAI continues to invest in the venture heavily, Altman has also expressed his concerns over safety measures to ensure that the tool doesn’t spiral out of control.
The FTC already launched an investigation into ChatGPT to determine whether the company has broken consumer protection laws.
So many talking UIs are not intuitive on windows on these handhelds, but one can still install steam and use it in big picture mode to get a steam deck like UI.
Also, there are launchers like playnite with many themes.
No thanks. We don’t need more closed and bloated spyware, what we need is more open and privacy respecing OSes like GNU/Linux and devices using it like Steam Deck.
No thanks. We don’t need more closed and bloated spyware, what we need is more open and privacy respecing OSes like GNU/Linux and devices using it like Steam Deck.
windowscentral.com
Newest