The AI Bubble and the U.S. Economy: How Long Do âHallucinationsâ Last? This paper argues that (i) we have reached âpeak GenAIâ in terms of current Large Language Models (LLMs); scaling (building more data centers and using more chips) will not take us further to the goal of âArtificial General Intelligenceâ (AGI); returns are diminishing rapidly; (ii) the AI-LLM industry and the larger U.S. economy are experiencing a speculative bubble, which is about to burst.
Why pay a celebrity podcast host millions when you can create your own using AI?
Inception Point AI is attempting to do just that, as the company builds a stable of AI talent to host podcasts, and eventually become broader influencers across social media, literature and more. Amid the high costs for producing narrative podcasts and pricy, short-term contracts for popular hosts, the idea here is being able to own, scale and control the talent (unlike those off-the-cuff humans) and produce shows at a minimal cost.
while doing some research earlier this week co-pilot offered to make me a personal podcast
i took them up on it with a related subject that i know well
co-pilot let me know it would take a couple of minutes and would notify me when ready
so far, so good
once it was ready i played the seven minute podcast which was in a conversational format between a male and female
it was very basic and co-pilot did a good job illustrating the subject framework
the cool thing is that it offered into more advanced/deeper detail if i wanted
Why pay a celebrity podcast host millions when you can create your own using AI?
Inception Point AI is attempting to do just that, as the company builds a stable of AI talent to host podcasts, and eventually become broader influencers across social media, literature and more. Amid the high costs for producing narrative podcasts and pricy, short-term contracts for popular hosts, the idea here is being able to own, scale and control the talent (unlike those off-the-cuff humans) and produce shows at a minimal cost.
Dr. Joleen Liang is Co-founder of Squirrel AI, which pioneered adaptive learning at scale, first in China and now in the US. By 2021 its technology had served over 60,000 public schools in 1,200 cities across Asia. Squirrel AI has implemented large knowledge graphs mapping out the main concepts in the K-12 math, science, and language curriculum. The Squirrel learning tablet actively observes student behavior (including eye-tracking during video lessons) and adapts its presentation and testing to individual learning patterns.
this channel/podcast is excellent
very good analysis
"Today, we're breaking down the MIT study claiming 95% of generative AI pilots at companies are failing - and why this headline is misleading the entire market. The report, based on just 52 interviews and 150 survey responses, has been cited as a reason for AI stock crashes, but the methodology is deeply flawed and the findings are being wildly misinterpreted. What the study actually reveals is that while individual employees are getting massive value from AI tools (90% use LLMs regularly vs only 40% of companies buying subscriptions), organizations are struggling with implementation - not because the technology doesn't work, but because of leadership buy-in, poor change management, and organizational dysfunction."
Google Xâs former chief business officer Mo Gawdat says the notion AI will create jobs is â100% crap,â and even warns that âincompetent CEOsâ are on the chopping block. The tech guru predicts that AGI will be better at everything than most humansâechoing the likes of Google DeepMind CEO Demis Hassabis and OpenAI chief Sam Altman. Only the best workers in their fields will keep their jobs âfor a while,â and even âevilâ government leaders might be replaced by the robots.
Some of this sounds a lot like the hysteria about fracking a few years back.
I worked in a facility that used groundwater for cooling and I'm on a well myself. I'm curious what these facilities are doing with the water. The facility I worked in (a crystal growth plant) pumped water out of the ground, ran it thru heat exchangers, then pumped it back into the ground via an injection well. Inside the plant we recirculated DI water to cool the equipment—no net consumption. All we did we heat up the earth. I don't know why they would need to actually consume water unless they are just heating it up and dumping it into the sewage treatment system, which would also put a strain on that infrastructure, which the article doesn't mention.
If your well runs dry (been there) you don't notice it because only some of the taps in your house don't work. None of them work. They all feed from the same tank.
Like most articles intended to induce some kind of panic reaction this one is heavy on breathless anecdotes and light on technical details—likely because those reporting them don't have the background to understand them, but also because they don't talk to any of the targets of their wrath.
Wells (and plumbing in general) have all kinds of problems for all kinds of reasons. This case is not closed.
