So, after watching that video "Capacitor Safety 101" posted in another forum, I was going to make a comment about how so many people seem to forget that electricity has 2 forces and not just 1 (attraction and repulsion).

So just for Ho Hos I did a search, and this was Copilot's answer, (even though I never even asked Copilot)

My post: Electricity has two forces, attraction and repulsion

Response:

Electricity is characterized by two fundamental forces: attraction and repulsion. These forces are responsible for the behavior of charged particles and play a crucial role in various physical phenomena. Here's a brief overview of how these forces operate:

Attraction: When two charged objects have the same sign (like charges), they attract each other. This means that two positively charged objects will pull away from each other, while two negatively charged objects will pull towards each other.

Repulsion: Conversely, when charged objects have opposite signs (unlike charges), they repel each other. This means that a positively charged object will push away a negatively charged object, and vice versa.

So, I got a kick out of that and decided not to post my comment in the video thread.

And you can bet that there are instructors out there shaking their heads right this minute as students submit answers like this, copied directly from an LLM, in response to homework questions. And you can also bet that some of those same students will be complaining about not getting full credit for their "work".

Been there, done that, wash, rinse, repeat.

I got in the habit of including in most homework assignments a problem that I worked, in full, in class. I never said that I would do that, as the intent was to provide a bit of a reward for people that came to class and actually paid attention. Sometimes those problems were only worked live on the board, but sometimes they were also included in the formal lecture slides, which were then made available on the course website.

The grades on those problems weren't markedly higher than on the other problems and they often showed the same telltales of people just throwing the question at an LLM and presenting the answer as their work, despite glaring errors. I routinely then had students complain (sometimes to the Dean) that I had never covered that material, even when it was an example that was worked in the posted lecture slides. I actually had one student, when asked why they didn't come to class, respond by asking why should they waste their time coming to class when they can get anything they need online. To which I pointed out that the fact that they scored less than 25% on the first exam would seem to refute that assertion.

 

 

OpenAI Researcher Quits, Saying Company Is Hiding the Truth

​

Now, Wired reports that the Sam Altman-led company is becoming more “guarded” about publishing research that paints an inconvenient truth: that AI could be bad for the economy.

 

"Slop" chosen as Merriam-Webster's 2025 word of the year

​

"Slop" was first used in the 1700s to mean soft mud, but it evolved more generally to mean something of little value. The definition has since expanded to mean "digital content of low quality that is produced usually in quantity by means of artificial intelligence."

 

"Slop" chosen as Merriam-Webster's 2025 word of the year

View attachment 360596​

If they are going to be asserting that that is a distinct definition of the word "slop", then they must have dozens and dozens of definitions listed for that word. Poor quality food, especially when cooked in large quantities, is referred to as "slop". Dirty cleaning water is also commonly referred to as "slop". As is food scraps collected and fed to animals such as pigs (as in "slop bucket").

The term "digital slop" is not some new definition of "slop" -- it is using it well within its current meaning of being something of little value. That the adjective ('digital') is left off when the context strongly implies that is just the way humans have always shortened phrases when the context can carry the extra information.

 

ChatGPT is a thin candy shell that covers a steaming pile of AI crap. It's not a search engine, it makes lies, has hallucinations and easily makes very impressive convincing garbage that's just flat wrong.
https://en.wikipedia.org/wiki/Hallucination_(artificial_intelligence)
https://forum.allaboutcircuits.com/...rn-faster-than-ai-for-now.146468/post-1786854

https://www.cdotrends.com/story/17744/google-scrambles-meet-chatgpt-threat

Truth. My granddaughter is too crazy about it. It's crap!

 

https://www.theregister.com/2025/12/09/google_fortifies_chrome_ai_with/

Google says Chrome's new AI creates risks only more AI can fix

'User Alignment Critic' will review agentic actions so bots don't do things like emptying your bank account

Google plans to add a second Gemini-based model to Chrome to address the security problems created by adding the first Gemini model to Chrome.

Even better solution, don't use 'AI'.

 

They put an AI vending machine in their office and it gave away everything:

An interesting take on implications and interpretations of AI-generated content:

 

https://9to5linux.com/firefox-will-ship-with-an-ai-kill-switch-to-completely-disable-all-ai-features

What was not made clear is that Firefox will also ship with an AI kill switch that will let users completely disable all the AI features that are included in Firefox. Mozilla shared this important update earlier today to make it clear to everyone that Firefox will still be a trusted web browser.

“Something that hasn’t been made clear: Firefox will have an option to completely disable all AI features. We’ve been calling it the AI kill switch internally. I’m sure it’ll ship with a less murderous name, but that’s how seriously and absolutely we’re taking this,” said Firefox developer Jake Archibald on Mastodon.

 

https://calmatters.org/environment/2025/12/data-center-energy-study-california/
Big Tech blocks California data center rules, leaving only a study requirement

All of these new, fancy, AI data-centers are potentially a big fat, juicy EMP/Power link target. Lots are in remote areas, with likely limited security support infrastructure. If these things eventually actually become useful, to the point they become critical infrastructure to the security of the country, maybe we should start to harden facilities like we did with the old ATT long-lines network.

 

https://garymarcus.substack.com/p/why-chatgpt-cant-be-trusted-with

Why was this happening? What I told Barrett (and which he quoted in his writeup of all this) was this:

Pure LLMs are inevitably stuck in the past, tied to when they are trained, and deeply limited in their inherent abilities to reason, search the web, “think” critically etc. … The unreliability of LLMs in the face of novelty is one of the core reasons why businesses shouldn’t trust LLMs

§

Of course, the LLM companies have armies of humans; in my own brief experiments a couple hours later, OpenAI had apparently already patched this particular problem.

But nobody should be surprised by these errors; they emanate from the same dynamics as hallucinations: pure LLMs correlate words in their training, but lack stable, revisable world models. Everything else is glommed on top, with more or less reliabilty.

So they forever play a game of catchup. Using massive numbers of humans (exact numbers unknown), GenAI companies perpetually put band-aids that they never disclose on top of their LLMs, based on human corrections, fixing each new problem as it arises. But the cycle repeats, endlessly.

https://commons.wikimedia.org/wiki/Fileresident_Nicolas_Maduro_on_board_the_USS_Iwo_Jima_(cropped)
Peanuts?

 

https://apnews.com/article/data-cen...e-nimby-tech-21fa7b957664d5dca6788e35ab43b88e
Big Tech’s fast-expanding plans for data centers are running into stiff community opposition

A growing number of proposals are going down in defeat, sounding alarms across the data center constellation of Big Tech firms, real estate developers, electric utilities, labor unions and more.
Andy Cvengros, who helps lead the data center practice at commercial real estate giant JLL, counted seven or eight deals he’d worked on in recent months that saw opponents going door-to-door, handing out shirts or putting signs in people’s yards.
“It’s becoming a huge problem,” Cvengros said.
Data Center Watch, a project of 10a Labs, an AI security consultancy, said it is seeing a sharp escalation in community, political and regulatory disruptions to data center development.

 

https://apnews.com/article/data-cen...e-nimby-tech-21fa7b957664d5dca6788e35ab43b88e
Big Tech’s fast-expanding plans for data centers are running into stiff community opposition

No worries, I am sure China will accommodate them. What could go wrong?

What was that? You want to review and approve all the training data? Sure we can do that.

 

https://www.msn.com/en-us/news/us/t...reshaping-the-political-landscape/ar-AA1TFdl2

The grassroots blowback comes from deep red states as much as from left-wing groups such as the Democratic Socialists of America, which have helped draw hundreds of residents to hearings in Arizona, Indiana and Maryland
...
“I don’t care how much chocolate icing you put on a dog turd, it don’t make it chocolate cake,” said Rick Plummer, who raises elite team-roping horses next to the proposed data center. “They are trying to fluff this data center thing up and say, ‘Man, eat this birthday cake.’ But it isn’t birthday cake.”

 

https://www.msn.com/en-us/news/us/t...reshaping-the-political-landscape/ar-AA1TFdl2

The grassroots blowback comes from deep red states as much as from left-wing groups such as the Democratic Socialists of America, which have helped draw hundreds of residents to hearings in Arizona, Indiana and Maryland
...
“I don’t care how much chocolate icing you put on a dog turd, it don’t make it chocolate cake,” said Rick Plummer, who raises elite team-roping horses next to the proposed data center. “They are trying to fluff this data center thing up and say, ‘Man, eat this birthday cake.’ But it isn’t birthday cake.”

Not surprising. We see it all the time. People want X and insist that we need more X (and often that government should promote more X). But providing X always has some negative aspects of it and many of those same people that demand it then insist that they not have to suffer any of the negative aspects of it. They still want X, just as long as someone else has to suffer the consequences.

This is true across the political spectrum -- it's basic human nature.

 

 

Seems its really just making it easier to write AI slop science papers instead of human slop science papers.
What actual new, novel scientific discoveries has 'AI' alone been responsible for to date? The base problem of new science discoveries is not intelligence, it's new data.

https://www.nytimes.com/2025/12/26/podcasts/hardfork-ai-science.html

Sam walks us through how Kosmos works, and why tools like it could dramatically speed up data analysis. But he also discusses why some of the most audacious claims about A.I. curing disease are unrealistic, as well as what bottlenecks still stand in the way of a true A.I.-accelerated future.
...
Newton: At this moment in 2025, how much do you think A.I. tools have changed the life of a working scientist, and how different do you expect that will be a year from now?

Rodriques: I think that you’d be shocked to the extent that they have not yet. Scientists in general are extremely conservative people because if you’re running an experiment, you never actually fully know, in biology at least, you usually do not fully understand why the experiment works and why not. There are some things that you’ve inherited from protocols that you’ve run in the past, and where it’s like we do it this way. You could go and test it, but there are way too many things to test. So, you’re just kind of locked in in your methods, and it’s what works, and you just want to do what works. And so for that reason biologists just adopt new methods slowly. I think most labs around the world are still probably doing science the way they’ve done it before, and probably will continue to do so for a while, and that’s OK. One place, I think, with coding, a lot of people are already adopting it, because in biology, historically, coding has been a big bottleneck. It’s a huge unlock now that biologists who didn’t know how to code can do a lot of coding using Claude Code, using OpenAI’s models, Gemini, et cetera. So, that’s a huge unlock. I think that that’s going to see a lot of adoption quickly. Literature search, right? Like being able to parse the immensity of the scientific literature, that’s a huge unlock, that’s going to get adopted very quickly. The tools like what we’re building are like a little bit more frontier. Ultimately, people will adopt them when they see other people using them and getting great results.

 

AI will definitely result in slop if there's no human to verify its output. But I think it'll prove to be an invaluable asset to speed things up that will help to "connect the dots" between facts and ideas when doing research, for instance.

It's a tool that can be used or misused depending on the person wielding it.

 

AI will definitely result in slop if there's no human to verify its output.

And here is the big problem. Human nature dictates that the vast majority of users will not verify its output, from students using it to do their homework, to doctors preparing their patient notes, to judges using it to write their opinions. All have been demonstrated.

 

I see the arrival of LLMs (I dislike calling the tech AI) as being similar to pocket calculators. Yes, they've made most people forget how to quickly make operations in their heads, but they have also made life the hell of a lot easier for most.

But LLMs are not like calculators, in the sense that their output is complex, and mostly based on previously reported criteria, and cannot quickly and easily be verified following a simple algorithm.

So I wonder if, in the near future, at least some LLMs will boast a certification of sorts guaranteeing they will never report unverified data ... and who would have the authority of administering said "certification"