AI Uses

[stylofone]

An long assessment of the internet's descent into madness. (original ft link provided to create preview, archive link for the whole article).

https://archive.is/H2Wjh

https://www.ft.com/content/5d06bbb4-003 ... 0ab74bedef

[pipbarber]

An long assessment of the internet's descent into madness. (original ft link provided to create preview, archive link for the whole article).

https://archive.is/H2Wjh

https://www.ft.com/content/5d06bbb4-003 ... 0ab74bedef

From that article.

We are faced, now, with a digital world defined by madness and hostility. Can we find a way back to an internet that puts people in lucid conversation with one another, where books are published after they are written, where anger and insanity aren’t the dominant modes of thought and the defining editorial values are more meaningful than a chumbox of clickbait nonsense? I’m not sure.

Well, i'm sure that this place here is a real and decent internet space. And that's why we need to work out how to keep our base group together, expand and resist internet insanity.

(tad off topic)

[The Saint]

Ai is fantastic.

But ....... it depends on how you use it.

Eg: I asked ChatGPT the following

What i the main point of article.
Does it mention that cannabis is more potent today than 50 years ago

https://www.ncbi.nlm.nih.gov/books/NBK425767/

ChatGPT's response.

Main Point of the Article
The primary objective of the article is to evaluate the current evidence on the health effects of cannabis and cannabinoids. It aims to provide a thorough analysis of both therapeutic and adverse effects, identify gaps in current research, and offer recommendations for future studies. The report covers a wide range of topics, including therapeutic uses, risks associated with cannabis use, and the impact of cannabis on various health outcomes.

Cannabis Potency Over Time
Yes, the article does mention that cannabis is more potent today than it was 50 years ago. It notes that the concentration of delta-9-tetrahydrocannabinol (THC), the primary psychoactive component of cannabis, has increased significantly over the past few decades. This rise in potency is attributed to selective breeding and advanced cultivation techniques aimed at producing cannabis strains with higher THC levels. The increased potency may have implications for both the therapeutic effects and potential risks associated with cannabis use.

.
I accidently left the 's' off the word 'is' but no big deal, Ai knows how to fix that kind of thing.

I have a friend who bombards me with philosophy articles, and I have now fallen into the habit of using ChatGPT to tell me the main points of them.
Regardless of whether what I am doing is good or bad, it saves a lot of time.
If ChatGPT's shortened explanation attracts my attention, then I might read the whole article. (But I rarely do)

Maybe if you have a short attention span, like I do, it is great, but for those who love reading and seeing the writer's perspective on a subject, then maybe what I am doing is somehow cheating, and my actions won't allow me to understand the writers perspective.

Another example of ChatGPT is to give insight into the meaning of paintings.

Eg, I inputted the following into ChatGPT

tell me the meanings of Landscape with the Fall of Icarus please

ChatGPT's response.

Description:
The painting shows a peaceful, everyday rural scene — a farmer plowing, a shepherd tending sheep, ships sailing — and in a small, almost hidden corner, the legs of Icarus disappearing into the sea.

Meanings & Themes:

Human Indifference to Suffering:
The central idea is that while Icarus is drowning (a dramatic mythological event), the world goes on as usual. No one notices or cares.

The Mundane vs. the Heroic:
The grandeur of Icarus's flight is overshadowed by the ordinary lives of regular people. It suggests that everyday life often continues untouched by even the most profound tragedies.

The Fallibility of Ambition:
Icarus flew too close to the sun out of pride or ambition. His fall is a reminder of human overreaching and the consequences of ignoring warnings.

Focus Shift:
Unlike traditional heroic art, which would center the tragedy, Bruegel's painting minimizes Icarus. This shift implies a new, more grounded perspective on life and death.

But it's explanation was nothing compared to my favourite explanation found on Youtube.

[stylofone]

Ai is fantastic.

I have a policy of not consuming any content which I know to be made with AI. Your use of the technology reminds me of this cartoon:

230327.n.aiwritten-59885806.jpg (102.58 KiB) Viewed 137 times

Generally I think that any AI-generated content is inferior to human-generated content. My view is, if you can't be bothered writing it, I can't be bothered reading it. Life is too short to read everything I want to read. AI makes that problem worse by filling the world with slop. Likewise, I won't write you a letter if I know you are not going to read it.

In your philosophy article example, AI could be preventing you from broadening your knowledge, improving your attention span, and sharing the interest with your friend.

I am pretty sure AI is a tech industry bubble, a promise of future utility whose main effect is to prop up the inflated value of tech stocks, which will collapse if the companies don't constantly create the expectation of innovation. When people work out that AI creates more shit than it flushes away, the bubble will burst. The process could accelerate as AI gets worse and the shit to shinola ratio increases, as outlined by this article, which is pretty concise.

https://www.theregister.com/2025/05/27/ ... _collapse/

[The Saint]

Generally I think that any AI-generated content is inferior to human-generated content

"Inferior content" yes, as I pointed out in the example I gave about the Ai explanation of " Landscape with the Fall of Icarus" compared to the human one.

And people are in fact complaining about the overuse of Ai
eg:

Ai is a tool.

A fantastic tool.

And that is all it is supposed to be, in my view.

Eg: Ai was used to crack the code for folding proteins.
Eg:

Unfortunately, mass media influencers on Twitter, Youtube, Facebook etc, push the narrative that Ai is going to replace us.
And in some cases I really hope it does eg: farm work, picking grapes in say Mildura, Victoria, the faster Ai and robots replace us in such jobs the better.
But then again, Ai and robots would be used as a tool in such a case.

Better to have Ai and robots used as a tool, rather than us humans used as a tool.

[stylofone]

Unfortunately, mass media influencers on Twitter, Youtube, Facebook etc, push the narrative that Ai is going to replace us.
And in some cases I really hope it does eg: farm work, picking grapes in say Mildura, Victoria, the faster Ai and robots replace us in such jobs the better.

I used to be excited by technology back in the early days of the internet when Wired magazine had a much higher ratio of content to advertising, and it clearly delineated which was which. Now I am irredeemably cynical. I need to keep myself open to the possibility that I am completely wrong and my conclusions are the result of an emotional disposition or bad reasoning, but so far my cynicism seems healthier.

I get the impression the "human replacement" narrative is an offshoot of the idea of the technological singularity, which has been promulgated by all sorts of people.

As for taking people's jobs, I find David Graeber's "bullshit jobs" hypothesis to be quite compelling, that many jobs are not meant to be productive, they are a sort of social construct made out of people who pretend to do useful things. But the main point is that it is people who are doing all this meaningless busy work. I suspect that the task of pretending to work could be done very easily by AI, but the pretence is meaningless if it's not done by people.

The other book influencing my brain at the moment is "Overshoot" by William Catton. In his assessment, fruit-picking robots would be a way of amplifying the extent of mass human die-off when we have a civilisational crash which cuts off our access to robot technology. Catton said the exhaustion of fossil fuels would inevitably bring on the crash, but it could come earlier due to climate change which became a bigger problem after he wrote the book in 1980. The robots might seem like they are a solution because they could pick fruit for us, but they actually make the problem worse. Even if it's not robots, technology is a doubling down on doom. Catton claims that when you take the entire energy expenditure into account, rice farming with 100% human labour, 19th century style, uses less energy than the modern system with trucks and tractors and machinery. Adding robots makes it even less efficient.

[pipbarber]

I'm naturally inclined towards Stylo's cynicism of ai but your point, Saint, that ai can be a useful tool in the right circumstances is obviously valid. The same debate is had over every new technology though, isn't it? The real question is who owns it and how is it used.

You've given two contrasting examples. Using ai to solve complex scientific problems is great. Using ai to negate the problems associated with reduced attention span will of course only compound the problem of reduced attention span, and that is a very very big problem in the context of a democratic citizenry making wise and informed electoral decisions, beside other psycho-social concerns.

And as for who owns and develops general purpose ai tools, well that would be some of the worst actors on the planet. People and corporations that are more than happy to reduce a population's capacity to focus on anything but the next endorphin rush of vacuous consumerism and the endless regurgitation of popular culture tropes.

My position is that ai could be a useful tool, but given the context, it's more likely to be a tool of enslavement, environmental destruction, poverty and oppression.

[The Saint]

My position is that ai could be a useful tool, but given the context, it's more likely to be a tool of enslavement, environmental destruction, poverty and oppression.

Yep, and there is one more point to be added to this list.

That point being the theft of intellectual property.

Ai, like ChatGPT, scrape the internet for anything and everything to answer questions, without paying anybody for the info it scrapes.

But "OpenAI partnered with Reddit in 2024 to access its content through a paid licensing deal."

Ai isn't really Ai, because it can not "think" for itself.

There is something known as "AI-to-AI degradation" or "model collapse."

This is where, when Ai only uses other Ai's to communicate and question, it becomes trivial over time.

It needs to scape the human content on the internet in order to give "intelligent" responses.

Ilia Shumailov wrote the most read paper on the subject and Nature magazine has also written about "model collapse."