AI - Starmers 50 point plan to be released (13/1/25)

[Serge Forward]

Or watch this. 23 mins.

23 minutes?!?? Thanks for the links all

 

[Sue]

"AI agents mean Salesforce won’t hire software engineers in 2025, apparently"

Strong opening

Salesforce.

 

[xenon]

There's a quite useful breakdown on Adam Conover's show across two episodes which goes into depth about both the market situation driving Big Tech's AI push and the broader state of things for those with a bit of podcast time on their hands. Zitron is a bit over-bearish about predicting burst bubbles but the base analysis seems pretty sound.





(That'll be it from me on YouTube links)

Just listening to the first one now. Cheers. This is good and articulates very well the general enshitification of tech products as well as the Emporer's New Clothes aspect of "AI." all tied up with the market's need for growth, fast growth, constant growth.

 

[magneze]

Zitron's podcast is quite entertaining. Although I wouldn't bother with the latest CES episodes.

 

[Crispy]

Zitron's podcast is quite entertaining. Although I wouldn't bother with the latest CES episodes.

Yeah, sounds like they had fun in Vegas but its just a bunch of Podcast Friends getting drunk and yakking it up

 

[magneze]

Yeah, sounds like they had fun in Vegas but its just a bunch of Podcast Friends getting drunk and yakking it up

Exactly how it came across to me.

 

[Saul Goodman]

For the Zitron interview, the first half is all about Enshittification in tech (chasing Number Go Up while actively making the actual products worse).
The second half is about the AI bubble.

You could read Zitron instead of listening to him.
1st half: Never Forgive Them
2nd half: The Subprime AI Crisis

He doesn't half write a lot of words though so get a comfy chair!

I asked ChatGPT to summarise that.

Could you summarise the content of a web page for me?

ChatGPT said:​

Sure! Please provide the URL or the text from the web page, and I can help summarize it for you.

You said:​

The Subprime AI Crisis

None of what I write in this newsletter is about sowing doubt or "hating," but a sober evaluation of where we are today and where we may end up on the current path. I believe that the artificial intelligence boom — which would be better described as a generative AI boom

www.wheresyoured.at

ChatGPT said:​

I currently can't access or view content directly from external websites. However, if you provide the text or key details from the page, I'd be happy to help summarize it for you!

 

[xenon]

Or if the dam thing could look at everyone's calendars and tell me when I can get all the people I need in the same room, that would be quite handy.

This is what I don't get. Everyone's luke (SP?) warm on Co Pilot. Microsoft seemingly can't even tell you what you can use it for. No case studies, no real world examples...

Why can't it do some boring but generally useful things like respond to verbal requests to search my inbox for messages from John and add a calander appointment if John has sent one. Find my document about Android accessibility and summarise it's content into a no more than 200 word email.


At my last job, it kept popping up in Edge when I was trying to use our web based CRM. Doing the whole clippy thing, hey I can see you're looking at a table of data, let me help etc. So I thought I'd give it an easy one and asked it how many rows... After 10 minutes it still hadn't come back with anything. The table was less than 20 rows, I just wanted to see if it could do something... Anything useful.

 

[xenon]

I hate reading chat GPT output on other people's questions. As I said on another thread, it's always so boring verbose and equivocating.

 

[Artaxerxes]

"AI agents mean Salesforce won’t hire software engineers in 2025, apparently"

Strong opening

As someone working with salesforce this is legitimately attractive to me

 

[UnderOpenSky]

I hate reading chat GPT output on other people's questions. As I said on another thread, it's always so boring verbose and equivocating.

I'm using ChatGPT a lot at the moment and you certainly need to give prompts to get it to stop that.

 

[UnderOpenSky]

I asked ChatGPT to summarise that.

Looks like this is a paid for feature.

In "The Subprime AI Crisis," Edward Zitron argues that the current generative AI boom is unsustainable and poised for collapse, potentially harming big tech companies, startups, and public perception of the tech industry.


He highlights several indicators of this impending downturn:


OpenAI's Financial Strain: OpenAI is seeking to raise substantial funds—at least $6.5 billion at a $150 billion valuation—and an additional $5 billion in debt. This aggressive fundraising is seen as a sign of financial instability.


Operational Challenges: The company faces increasing operational costs, with projected losses of $5 billion in 2024. Training more advanced AI models may require investments up to $100 billion, raising concerns about the sustainability of such expenditures.


Industry-Wide Implications: Zitron warns that the collapse of the AI bubble could lead to significant job losses and damage the broader tech ecosystem. He emphasizes the need for a sober evaluation of the current trajectory and its potential human cost.


Overall, Zitron calls for a critical reassessment of the generative AI industry's direction, cautioning against unchecked growth and the pursuit of unsustainable advancements

 

[rasputin]

 

[Kevbad the Bad]

Essentially nobody knows what the impact of AI will be on the economy, the NHS, society, warfare or anything else. That includes Starmer, of course, and all his cabinet. In effect he is saying "vote for my policy which will have unforeseen consequences. If we don't do this some other country will reap the benefits of whatever happens, if it happens, before we do." Crap isn't it?

 

[Saul Goodman]

Looks like this is a paid for feature.

I asked the app the same question...

In "The Subprime AI Crisis," Ed Zitron discusses the unsustainable nature of the current generative AI boom. He argues that many AI companies are integrating generative AI at prices that are far from stable and even further from profitable. Zitron highlights that companies like OpenAI and Anthropic are deeply unprofitable, with pricing strategies designed to attract customers rather than generate profit. He warns that this situation could lead to significant consequences for big tech, the startup ecosystem, and public perception of the tech industry.

Zitron also points out that OpenAI is attempting to raise substantial funds, including a $5 billion debt facility, indicating financial instability. He suggests that the AI industry is in a precarious position, with the potential for a significant downturn that could impact many individuals and companies.

 

[Petcha]

Is that AI forum ever going to be set up?

I think this illustrates that it's not just Technology, it's far more complex than that

 

[Dogsauce]

Call me a cynic, but the "AI will fix everything" approach smacks of the "the Internet will fix everything" approach of the 90s.

Didn’t we get ‘biotech hubs’ sometime in the middle of those two? What happened to that?

 

[Artaxerxes]

 

[Santino]

Still waiting for an Industrial Revolution forum.

 

[SpookyFrank]

Is that AI forum ever going to be set up?

I think this illustrates that it's not just Technology, it's far more complex than that

I think we should avoid buying into this idea that AI is a force of nature and the next big thing for mankind. What it actually is is a handful of very complicated boondoggles whose usefulness and influence may have already peaked, insofar as it was ever real in the first place.

 

[Artaxerxes]

AI is also a whole toolkit of things, ranging from the actually useful translation algorithms to the absolute farce of ruining your google results so trying to split out to a dedicated AI forum would need to first answer the question of what is AI.


(its also largely not AI, its a repeating machine that shits out text and images based on previously defined algorthims, often made from datasets compiled by people in third world countries for poverty wages)

 

[Petcha]

I think we should avoid buying into this idea that AI is a force of nature and the next big thing for mankind. What it actually is is a handful of very complicated boondoggles whose usefulness and influence may have already peaked, insofar as it was ever real in the first place.

I disagree. It's a revolution on a par with the arrival of the web. And to be ignored at your peril.

And it goes far beyond the likes of ChatGPT etc, it will permeate everything, in the space of a few years. Max.

 

[SpookyFrank]

I mean if you need proof that AI is a dead duck, just read the thread title. Keir Starmer thinks it's a good idea.

 

[Buddy Bradley]

The really important question is when are we getting replicators.

 

[Petcha]

I mean if you need proof that AI is a dead duck, just read the thread title. Kier Starmer thinks it's a good idea.

25 years on, here are the worst ever predictions about the internet

Back in the Nineties, many experts didn't think the internet would live to see its first, let alone 25th, Internaut Day.

www.newstatesman.com

Are you Cliff Stoll?

 

[brogdale]

I mean if you need proof that AI is a dead duck, just read the thread title. Kier Starmer thinks it's a good idea.

I can't really read about this topic without hearing Adam Curtis intoning over a grainy clip of some irrelevant scene that...Even as Mr Starmer was addressing the people of the UK about AI, some 3 thousand miles away....

 

[sleaterkinney]

What questions are we going to ask it?. What special insight is it going to give that we don't already know?.

It's just selling off our data for $

 

[Artaxerxes]

The really important question is when are we getting replicators.

I don't think we want those.

 

[magneze]

Earlier I wondered if any journalists will ask interesting questions, potentially about the ownership of output of this new initiative. Predictably, the questions from mainstream journalists were utter shit:

"If the country is run by AI, won’t that put the country at risk of being hacked?"

"Won’t AI always try to increase its power. If it is running the MoD, couldn’t it declare war?"

 

[tommers]

Earlier I wondered if any journalists will ask interesting questions, potentially about the ownership of output of this new initiative. Predictably, the questions from mainstream journalists were utter shit:

"If the country is run by AI, won’t that put the country at risk of being hacked?"

"Won’t AI always try to increase its power. If it is running the MoD, couldn’t it declare war?"

Genuinely, what is wrong with these people?