this post was submitted on 16 Aug 2023
223 points (87.8% liked)

Technology

35125 readers
58 users here now

This is the official technology community of Lemmy.ml for all news related to creation and use of technology, and to facilitate civil, meaningful discussion around it.


Ask in DM before posting product reviews or ads. All such posts otherwise are subject to removal.


Rules:

1: All Lemmy rules apply

2: Do not post low effort posts

3: NEVER post naziped*gore stuff

4: Always post article URLs or their archived version URLs as sources, NOT screenshots. Help the blind users.

5: personal rants of Big Tech CEOs like Elon Musk are unwelcome (does not include posts about their companies affecting wide range of people)

6: no advertisement posts unless verified as legitimate and non-exploitative/non-consumerist

7: crypto related posts, unless essential, are disallowed

founded 5 years ago
MODERATORS
 

Investors are barely breaking even as the venture is hardly making any profits due to a shortage of chips, divided interests, and more.

... OpenAI has already seen a $540 million loss since debuting ChatGPT.

... OpenAI uses approximately 700,000 dollars to run the tool daily.


⚠️ First off, apologies as I didn't cross check. Take it w/ a grain of salt.


This piece of news, if true, somehow explains why OpenAI has been coming up w/ weird schemes for making $$$ like entering the content moderation space.

On a similar note, I wonder if this had been a key driver (behind the scenes) in the recent investment in open source AI initiatives (Haidra comes to my mind?) Perhaps some corporations who haven't got enough $$$ to fund their own dedicated research group are looking to benefit from an open source model?

top 50 comments
sorted by: hot top controversial new old
[–] Clymene@lemmy.ml 67 points 1 year ago (3 children)

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.

[–] Uranium3006@kbin.social 31 points 1 year ago (1 children)

honestly I'd rather open source AI I can run locally. even for something like GPT4 an enterprise-scale operation could afford the hardware

[–] GlitzyArmrest@lemmy.world 4 points 1 year ago (1 children)

Have you heard of GPT4All?

[–] Uranium3006@kbin.social 3 points 1 year ago (1 children)

I'm aware of local AI but you need a really beefy GPU to run even the smaller models, and the good shit is good because it's big

load more comments (1 replies)
[–] Ubermeisters@lemmy.zip 8 points 1 year ago* (last edited 1 year ago) (7 children)

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.

load more comments (7 replies)
load more comments (1 replies)
[–] j4k3@lemmy.world 50 points 1 year ago (3 children)

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.

[–] TheEntity@kbin.social 85 points 1 year ago (3 children)

people will never be okay with the level of intrusive data mining required for OpenAI or Google’s business model

Where do you meet these people? I need more of such people in my life.

[–] Riker_Maneuver@startrek.website 27 points 1 year ago

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.

[–] drlecompte@discuss.tchncs.de 11 points 1 year ago

'People' in this respect are also the owners of media sites.

[–] HumbertTetere@feddit.de 7 points 1 year ago

There's currently a meeting in Germany with about 4000 of them.

But it's not the prevailing mindset in the general population.

[–] griD@feddit.de 16 points 1 year ago

AI is the framework of a new digital economy, not the product.

That is one interesting sentence. Thanks.

[–] krellor@kbin.social 4 points 1 year ago (1 children)

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.

[–] drlecompte@discuss.tchncs.de 3 points 1 year ago (1 children)

Yeah, but not models that are trained on data that raises copyright concerns, which is currently the case.

[–] AngrilyEatingMuffins@kbin.social 8 points 1 year ago* (last edited 1 year ago)

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

[–] Maximilious@kbin.social 38 points 1 year ago (4 children)

Have they asked the engine how they can generate more revenue?

[–] Tigbitties@kbin.social 16 points 1 year ago

$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.

[–] Ubermeisters@lemmy.zip 7 points 1 year ago

It's answer was 42

[–] Fissionami@lemmy.ml 7 points 1 year ago

The Prompt:
How OpenAI can generate more revenue?

The Response:
OpenAI, the organization behind the development of AI models like GPT-3, has a few strategies to generate revenue:

  1. 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.

  2. 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.

  3. 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.

  4. Premium Features: OpenAI could offer advanced features, improved performance, or specialized functionality as part of premium packages, enticing users to upgrade their subscriptions.

  5. Partnerships and Collaborations: OpenAI can collaborate with other tech companies, research institutions, or industries to jointly develop and commercialize AI applications.

  6. Consulting and Services: OpenAI could provide consulting services, training, and expertise in AI technology to help organizations integrate AI into their operations effectively.

  7. Training and Workshops: OpenAI can offer training programs, workshops, and educational resources to help individuals and businesses better understand and utilize AI.

  8. Data Services: OpenAI can offer datasets, annotations, and data-related services to researchers, businesses, and developers working on machine learning projects.

  9. Vertical-Specific Solutions: Developing AI solutions tailored for specific industries, such as healthcare, finance, or marketing, and offering them as industry-specific packages.

  10. 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.

load more comments (1 replies)
[–] donuts@kbin.social 29 points 1 year ago (4 children)

AI as a business is already running on fumes, and it's going to become even more expensive once intellectual property law catches up to them. We can only hope that the AI bubble bursting doesn't take the entire market economy down with it...

[–] Taako_Tuesday@lemmy.ca 14 points 1 year ago* (last edited 1 year ago) (1 children)

At this point there are so many bubbles, the question is which one will burst first

[–] GlitzyArmrest@lemmy.world 7 points 1 year ago

Didn't the tech bubble burst already?

[–] borlax@lemmy.borlax.com 10 points 1 year ago (1 children)

Or we can hope that it does take the entire market economy down with it...

[–] donuts@kbin.social 2 points 1 year ago (1 children)

I mean, I get you, but personally I don't really like the idea of millions of innocent people losing their homes and most of their savings because some fucking dweebs decided to put all of our collective wealth in legally dubious automatic junk "content" generators. I've lived through enough crashes to know that it's never the big guys that get fucked when everything goes tits up, it's us, our parents, our grandparents, etc.

load more comments (1 replies)
load more comments (2 replies)
[–] saud@lemmy.ml 29 points 1 year ago (3 children)

I really don't understand how this is possible when Microsoft has invested billions into OpenAI

[–] atticus88th@lemmy.world 17 points 1 year ago

All it takes is a couple of dudes to buy a couple of yachts, private planes maybe another home or two. And poof. Its gone.

[–] Jessper@beehaw.org 14 points 1 year ago (1 children)

It isn't. The article is obviously wrong.

[–] Peanutbjelly@sopuli.xyz 11 points 1 year ago

And you are the only voice of reason in this thread.

"Make up shit that makes OpenAI look bad" is like tech article gold right now. The amount of times i am seeing "look what ChatGPT said!!!" As if prompter intention is completely irrelevant to model output.

Objectivity doesn't exist anymore. It's just really popular to talk shit about ai right now.

Like when Altman effectively said "we should only regulate models as big or bigger than ours, we should not regulate small independent or open source models and businesses" to Congress, which was followed by endless articles saying "Sam Altman wants to regulate open source and stamp out smaller competition!"

I have no love for how unopen they've become, but at least align criticisms with reality please.

[–] Uncle_Bagel@midwest.social 8 points 1 year ago

Burning through billions of investors money isnt the same as being profitable. The Silicon Valley gravy train is over, and investors are actually demanding to start seeing returns on their investments.

[–] oldlamps@sh.itjust.works 24 points 1 year ago (2 children)

Things really move fast in AI, huh

load more comments (2 replies)
[–] deFrisselle@lemmy.sdf.org 15 points 1 year ago (1 children)

MS will buy it all at the fire sale for cheap then integrate it deeply into Bing, Windows, etc

load more comments (1 replies)
[–] boyi@lemmy.sdf.org 14 points 1 year ago* (last edited 1 year ago)

Sorry to say, I would take this with grain of salt. Not making profits is part of business model of these pioneering companies. Google, Amazon and Uber (etc) were in the negatives for so many years and they absorbed the losses in order to be the dominant brands where at the end users become dependent on them. At that point they'll start to charge exorbitantly and forcefully add unneeded features that will exert more control upon their users but there's nothing that they can do but pay, for the simple fact that they can't do without them.

[–] miss_brainfart@lemmy.ml 13 points 1 year ago

This is hilarious if true

[–] roguetrick@kbin.social 10 points 1 year ago

High interest rates baby. I noted this was happening when people were complaining about lowered quality because they were using less resource intensive operations.

[–] mojo@lemm.ee 10 points 1 year ago

They also didn't design ChatGPT to be power efficient at all, so that's bloating up their operating costs a ton.

[–] codepengu1n@feddit.it 8 points 1 year ago (1 children)

If Twitter ran for decades on a loss, so will OpenAI. Worst case scenario they get completely absorbed by MS and have the bill footed by them. Kind of what happened with Youtube.

[–] worfamerryman@beehaw.org 7 points 1 year ago (4 children)

One of the reasons tech companies were able to operate for a long time at a loss was due to interest rates being really low.

I think the increased interest rates are the reason for twitter, reddit, and other companies trying to monetize harder.

I could be wrong, I am not an economist. This is just the kind of stuff, I have read in other subs.

load more comments (4 replies)
[–] tourist@community.destinovate.com 8 points 1 year ago (1 children)

How do I approach a VC firm about losing all their money in a big spectacle? Seems to be all the rage these days.

load more comments (1 replies)
[–] autotldr@lemmings.world 8 points 1 year ago

This is the best summary I could come up with:


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.


I'm a bot and I'm open source!

[–] wahming@monyet.cc 8 points 1 year ago

It's kinda hilarious how many people are swallowing this article without any salt whatsoever.

[–] veloxy@lemm.ee 7 points 1 year ago

Did they try turning it off and not on again? 🙃

[–] library_napper@monyet.cc 6 points 1 year ago (1 children)

If they go bankrupt, what happens to their IP? Does it suddenly become public domain?

[–] 8ace40@programming.dev 14 points 1 year ago

I think it would be auctioned and sold to the highest bidder.

[–] Topdog@lemmy.ml 6 points 1 year ago
[–] victron@programming.dev 4 points 1 year ago

That was a quick bubble

[–] philluminati@lemmy.ml 4 points 1 year ago (1 children)

Uber has never turned a profit for 14 years. I’m guessing it’s windows central who is facing bankruptcy, intellectually speaking.

[–] Semi-Hemi-Demigod@kbin.social 3 points 1 year ago (2 children)

I wonder what song it will sing when they finally pull the plug

load more comments (2 replies)
load more comments
view more: next ›