LLM providers on the cusp of an 'extinction' phase as capex realities bite

Just out of curiosity, I wish online LLMs would show real-time power usage and actual dollar costs as you interact with it. It would be so insightful to understand to which degree the technology is subsidized and what the actual value&#x2F;cost ratio is.<p>I&#x27;ve read somewhere that generating a single AI image draws as much power as a full smartphone charge.<p>In case the suspicion is true that costs are too high to be monetized, then the current scale-up phase is going to be interesting. Right now people infrequently have a chat with AI. That&#x27;s quite a different scenario from having it integrated across every stack and it constantly being used in the background, by billions of people.<p>Late as they may be, for the consumer space I think Apple is clever to push as much as possible to the local device.

Shortly after ChatGPT hit the scene, everyone said &quot;Google invented this technology, how could they fall so far behind in commercializing it, haha they&#x27;re IBM now&quot;.<p>Maybe they didn&#x27;t fall behind in anything, maybe they just did an analysis of what it would cost to train transformer models with hundreds of billions of parameters, to run inferencing on them, and then decided that there was no way to actually be profitable doing this.

I&#x27;m using the (more expensive) Gemini 2.5 pro and it&#x27;s like talking to an adult again after claud went all RFK Jr. Brain Worm on me.<p>People have mentioned on hacker news that there seems to kind of &quot;weather patterns&quot; with how hard the various llms think, like during business hours they get stupid. But of course there is some disagreement about what &quot;business hours&quot; are. It&#x27;s one of those &quot;vibes&quot;.<p>Imagine scheduling your life around the moods of AIs.<p>That&#x27;s the business model. If you don&#x27;t want a surly and moody AI with a hangover and bad attitude, you gotta pay more!<p>Like isitdownrightnow.com for crowd sourcing web site availability, there should be a isitdumbrightnow.ai site!

<i>&gt; As the global tech research company forecasts worldwide generative AI (GenAI) spending will reach $644 billion in 2025, up around 76 percent from 2024</i><p>I’m having a hard time squaring the number <i>$644 billion</i> and the phrase “extinction phase.”<p>I don’t believe their actual estimate of GenAI spending but if it’s even in the same ballpark as the real value, that’s not an extinction.

Ads will eventually make their way into the responses or side bars. It will be interesting (and depressing) to see who does it first and who holds out hoping to squeeze out the ad-supported LLM providers.

In the light of this article, it makes sense that OpenAI are taking a &quot;lmao we dont even pretend to care&quot; approach to safety and intellectual property right now.<p>Altman loudly hyping &quot;look you can ghibli-fy yourself&quot;, stating inflammatory things like &quot;we are the death of the graphic designer&quot;; a desparate ploy to rapidly consume the market before the bubble bursts.

It took Amazon around six to seven years to see its first profitable quarter, and they still went into the red sometimes when doing major investments thereafter.

A slow pruning here seems healthy.<p>The more interesting question to me is how gpu vs tpu plays out. Plus the other npu like approaches. Sambanova cerebras groq etc

It sounds like you probably mean OPEX, I mean unless you explicitly are talking about loan payments.

Found funny that for something that is pretty much a commodity at this point, adoption seems to be the most important metrics.<p>Yes, there are differences between the models, and yes some may work better.<p>But picking the model at this point is just picking the cheapest option. For most use cases any model will do.

and how much value would be lost?