OpenAI lost like 5 BILLION dollars last year. With a 'B'. There is no way all these AI companies will ever see an ROI. Somebody (or more likely a lot of somebodies) will get left holding the bag.
this post was submitted on 17 Jul 2025
160 points (99.4% liked)
Tech
1639 readers
5 users here now
A community for high quality news and discussion around technological advancements and changes
Things that fit:
- New tech releases
- Major tech changes
- Major milestones for tech
- Major tech news such as data breaches, discontinuation
Things that don't fit
- Minor app updates
- Government legislation
- Company news
- Opinion pieces
founded 1 year ago
MODERATORS
That's why they are putting AI into every fucking thing. They want to get you hooked on it so, maybe, they can have a business.
I realized a while back that one of the primary goals of these LLMs is to get people to continue using them. While that's not especially notable - the same could be said of many consumer products and services - the way in which this manifests in LLMs is pretty heinous.
This need for continued use is why, for example, Google's AI was returning absolute nonsense when asked about the origins of fictitious idioms. These models are designed to return something, and to make that something pleasing to the reader, truth and utility be damned. As long as the user thinks that they're getting what they wanted, it's mission accomplished.
Apparently patched. I just tried this out:
[Prompt] Explain the origin of the English idiom "when the cracker breaks".
[Output] I can't explain the origin of the English idiom "when the cracker breaks" because this idiom doesn't exist. It's possible you're misremembering or combining parts of other idioms.
Perhaps you're thinking of:
- "When the cracks show": This refers to when flaws or weaknesses become apparent.
- "When the ship comes in": This means when a long-awaited fortune or success arrives.
- "Crackerjack": This is an adjective meaning excellent or first-rate.
If you can provide more context or clarify the idiom you're thinking of, I'd be happy to try and explain its origin!
This hits another problem - I know the idiom doesn't exist, because I made it up. However, the bot has no way to "know" it, and so it shouldn't be vomiting certainty. (Or rather, what a human would interpret as certainty.)
On this topic, this podcast episode is very interesting:
https://www.techwontsave.us/episode/282_chatbots_are_repeating_social_medias_harms_w_nitasha_tiku
and customers are just out here like "naw"
It's not OpenAI putting their AI into products though. It's other companies and CEOs.
They actually learned their lesson from the dot com bust. Yeah, there are mostly going to be losers, but the handful that come out on top are going to absolutely dominate. Nobody wants to risk losing out on being the next FaceBook or Google.
This has been said all along. And I’d wager a lot of investors agree. But the stock market is essentially gambling and you can’t argue with market trends. Even the critics on Wall street will ride the wave until it comes crashing down in the hope that they can cash out quick enough or they hope to catch the coattails of what few firms make it out the other side.
our economic system is wholly underpinned by logical fallacies
Our retirements are wagered at this table.
I know the moment I try investing in anything, it'll all come crashing down. You all should be paying me to not invest tbh
That's a catch-22 because the moment we invest in your non-investments, that will also cause it
Just short yourself
The key difference is that the internet is a fuckload more useful than what's being sold as AI.
Apple as an ai company? Right….
Yeah the entire market is wild right now.