AI and it's usefulness in everyday life?

[paulsharvey]

So, I really haven't messed with AI much, but when son bought his project truck, someone on here copied and pasted ChapGPT's answers. Which honestly where pretty good. Then wife needed to update a resume, she said ChatGPT made it a breeze. I went ahead and downloaded Deepseek, and have used it some, about fish species to stock in a pond. Wife uploaded a picture of the snake i shot this morning in the chicken coop to Chat and got the species, Eastern Rat snake.

I know in my house, we aren't using it anywhere near to its potential. How are you guys using it, in a productive way. I'm not talking about generating Memes, or whether it's taking jobs. Not meant to be a "should" or "shouldn't"; it's here and real, so how are you using it?

 

[CalG]

So, I really haven't messed with AI much, but when son bought his project truck, someone on here copied and pasted ChapGPT's answers. Which honestly where pretty good. Then wife needed to update a resume, she said ChatGPT made it a breeze. I went ahead and downloaded Deepseek, and have used it some, about fish species to stock in a pond. Wife uploaded a picture of the snake i shot this morning in the chicken coop to Chat and got the species, Eastern Rat snake.

I know in my house, we aren't using it anywhere near to its potential. How are you guys using it, in a productive way. I'm not talking about generating Memes, or whether it's taking jobs. Not meant to be a "should" or "shouldn't"; it's here and real, so how are you using it?

All our "information " access hasn't improved the quality of life, pulled anyone out of poverty, nor stopped any conflicts.

Call the ai thing a distraction, a waste of time, and worse when it comes to the essence.

 

[bigtiller]

I used to be able to holler into my cell phone "hey google" and I could ask a basic question and get an answer.

Something happened, and now "hey google" turned into "ask Gemini". I asked what love song from the 70's had a single word title that began with the letter C.

Actually, it wasn't that simple. We carried on a 2 way conversation for well over a minute. She would offer me a few choices, and the third time she picked the song I was thinking of. Cherish, by The Association.

Amazing!!

 

[paulsharvey]

All our "information " access hasn't improved the quality of life, pulled anyone out of poverty, nor stopped any conflicts.

Call the ai thing a distraction, a waste of time, and worse when it comes to the essence.

I'm not really sure that's true. I'm Not an early adopter of most tech, but normally once I find a use for it, I use it. Remember Google Earth, I had never used it until reading an article in a fishing magazine about the number of hidden lakes/ponds, and finding them on this aerial view app, Google Earth. I have used it to find lots of stuff, and we use it a lot at work. I use YouTube to find lots of useful information, everything from learning to reload, to repairing vehicles.

I will go ahead and say, yes, probably 90%+ of it is "entertainment/goofing off/what you do instead of watching TV to relax", but I don't think you can say there has been no improvement.

As I heard once, in each town, there was a last guy using a horse and buggy; and you don't want to be that guy.

Edit: one rereading, I think maybe you mean a macro sense, and that might be part of the difference. I'm not trying to make the world a better place, pull people out of poverty, or prevent wars; I've (all of us) have been give a tool, and I'm not entirely sure how to best use it, and I'm curious how others are using their new tool. Now, sure, you can leave the new tool in the box, but it doesn't mean it's not there, and others aren't using it.

 

[HawkinsHollow]

I have rather negative views on it as well. In my opinion it is just one more way technology is making us weaker. Doing things for us that we once had to do for ourselves. Like map reading, how many people can get somewhere today without their navigation software? But this goes to whole new levels. You will never have to write anything ever again, just ask AI to write it for you. Ask AI to summarize a book for you, boom, you no longer have to read those pesky books. And then the potential for things to go REALLY wrong once it becomes autonomous.

Have I heard of good uses for AI, yes I have. Like summarizing a contract, who ever reads those things? Now AI can do it for you.

I just think it is a slippery slope. What will we have to do for ourselves in 20 years? Technology has made the human race weaker since the industrial revolution, AI will just accelerate that IMHO. Will I be using it at some point? I am sure I will. But I want to be able to tell you I told you so, so I will be over here driving my horse and buggy for a while longer.

 

[paulsharvey]

BTW, I dont necessarily disagree about it being a double edged sword, and eventually causing issues, and possibly being a net negative. My point is, it's here, so I'm wondering how everyone is putting it to work for themselves.

 

[Eagle1]

It is being used successfully to scam the education system out of grants

Fake student aid: California colleges detect more fraudsters stealing millions
In 2021, the California Community Colleges Chancellor’s Office reported that about 20% of college applicants were likely fake. In January 2024, the state said it was up to about 25%.

They say scammers are increasingly relying on artificial intelligence to infiltrate classes, using tools like ChatGPT to pose as students. Students say these fraudsters are taking coveted seats and preventing them from enrolling in classes they need to graduate.

 

[CPTKILLER]

In a previous life in graduate school and later in engineering, I researched information. It remains a habit in my life. When I need information, I no longer have access to university libraries or their research. Additionally, I often can’t use proprietary data from companies.

AI can be useful for:

Parts and part numbers
Maintenance and assembly techniques
Legal issues in rural areas with limited access to resources

 

[paulsharvey]

So, for an example, cause this is a tractor forum. I asked Deepseek the text below.

"cheap aftermarket radiator to fit a kioti ck2610"

For a **Kioti CK2610 tractor**, finding a **cheap aftermarket radiator** requires matching the OEM specs while ensuring proper fitment. Here are the best budget-friendly options:

---

### **1. Affordable Aftermarket Radiators for Kioti CK2610**
| **Brand/Model** | **Price Range** | **Where to Buy** | **Notes** |
|----------------|---------------|----------------|----------|
| **Spectra Premium CU980** | ~$120–$180 | Amazon, eBay, RockAuto | Aluminum core, direct-fit for many compact tractors |
| **TYG Aluminum Radiator** | ~$150–$220 | Amazon, Walmart | Universal fit, may require minor mods |
| **Mishimoto MMHOSE-KT2610** (Custom) | ~$200–$300 | Mishimoto, Summit Racing | High-quality aftermarket, better cooling |
| **Chinese Generic (eBay/Alibaba)** | ~$80–$150 | eBay, Alibaba | Risky fitment, check seller reviews |

---

### **2. OEM vs. Aftermarket Cost Comparison**
- **OEM Kioti Radiator:** **$300–$500** (Dealer)
- **Aftermarket:** **$80–$250** (Significant savings, but verify compatibility)

---

### **3. Key Fitment Checks Before Buying**
**Dimensions:** Compare to OEM (approx. **22" x 18" x 2"** for CK2610).
**Inlet/Outlet Size:** Should match OEM hose diameters.
**Mounting Brackets:** Ensure bolt holes align.
**Material:** Aluminum is best for durability.

---

### **4. Where to Buy Cheap Radiators**
- **Amazon** ([Spectra CU980](https://www.amazon.com))
- **eBay** (Search *"Kioti CK2610 Radiator"*)
- **TractorPartsASAP** (Budget tractor parts)
- **Walmart Online** (TYG radiators)

---

### **5. Installation Tips**
- **Flush the system** before installing a new radiator.
- **Check hoses & clamps**—replace if worn.
- **Avoid ultra-cheap no-name brands**—leaks are common.

---

### **Best Budget Pick:**
**Spectra Premium CU980 (~$150)** – Reliable balance of cost and quality.

Need help finding a seller with confirmed fitment? Let me know!


So, based on that, I would then try to get some additional info on a Spectra CU980. I would Not blindly just order it; but for instance, it just spit that out in 10 seconds, vs probably several hours of hunting OEM SKUs, comparing model numbers, cross referencing, and still finding nothing less than $480.

 

[paulsharvey]

I guess I think of it like the old saying about fire. It's a great servant, but a terrible master

 

[HawkinsHollow]

CBS news just out this spot on AI a couple of days ago.

 

[ericm979]

I avoid it as much as possible. I'm not being a Luddite; my career was in tech. I have a pretty good understanding of how current "AI" works.

Current AI LLMs have a lot of problems:
-they're trained on material illegally scraped from the internet in violation of copyright law
-they're set up to emit plausible sounding information to a prompt. That information being accurate is not a goal nor is it possible with current LLMs
-they're being used to produce garbage writing to replace stuff (i.e documentation) that used to be written by humans who at least tried to be accurate.
-they're massively over hyped. They're not AGI or even close.
-bosses and investors are excited because they hope to replace employees. What is that going to do to society?
-current LLMs are not AI- they're not intelligent. They have no thought or understanding of meaning. Its just statistically generated tokens.

The kind of pattern matching that's used in LLMs does have some real uses. For example identifying cancer cells in imaging, or identifying small wildfire starts on camera. But it's not intelligence.

 

[EddieWalker]

I haven't used it unless we count auto correct, which seems to be a lot better then it used to be. Especially with punctuation.

My wife teaches at the local university. At first, students were using it to cheat, but then the teachers figured out how to use AI to detect cheating. It's very good at that, especially plagerism. It rates every paper on what percentage of it has been used before in other papers. Most are about ten percent, but the cheaters always get carried away and they come in at 80 to 100% copied from other papers.

What she likes the most about it is in writing questions for exams. There is a massive black market for exam questions and answers, so they have to write new questions for every test. AI has made this a lot easier.

 

[Oaktree]

All our "information " access hasn't improved the quality of life, pulled anyone out of poverty, nor stopped any conflicts.

Call the ai thing a distraction, a waste of time, and worse when it comes to the essence.

I wouldn't say that, sure makes it easy when you want to know how to do something to be able to Google it and have the answer in less than a second. I do think the "internet" has contributed to the polarization in the country today...there's less and less need to associate with people you don't agree with. I don't see that as a good thing.

I'll be the first to admit I really don't understand it, nor do I have the slightest idea how you'd use it (at least knowingly...I'm sure something like a Google search involves AI in some form)

I asked what love song from the 70's had a single word title that began with the letter C.

Actually, it wasn't that simple. We carried on a 2 way conversation for well over a minute. She would offer me a few choices, and the third time she picked the song I was thinking of. Cherish, by The Association.

"Cherish" wasn't a 70s song, it came out in the summer of 1966.

Today in 1966: The Association’s “Cherish” Hits the Hot 100 | Rhino

52 years ago today, The Association’s most durable hit single made its debut on the Hot 100. That’s not to say that it’s your personal favorite, but given how successful it was at the time of its release and how many times it’s been covered over the years, not to mention how much airplay it...

www.rhino.com

 

[CalG]

The BIG issue that concerns me is how willing people (sheep) are to accept whatever ai spits out as the god's honest truth and the "only way".

And yet it can only spit back what goes in.

Wikipedia is like that, but,,,,

Look! A squirrel!

 

[otlski]

I have interacted with AI in a few ways. Before getting into that, let me say that at this point I would not trust AI to opine or report on any controversial topic. That said, doing such was my first real interaction.

At the beginning of the Ukraine Russia war I chatted with an AI asking its opinion on what was happening. I choose that topic specifically because people had a hard enough time discussing it, so the mark of a good AI might be to pull off the conversation well. It was not. The chat seemed very forced. The AI was full of "facts" and insisted in hedging every word. Seriously noncommittal. I tried to force it down more committed avenues, but in the end it simply regurgitated and added nothing of value to the "conversation".

In another case, I wanted to test AI's ability to write marketing content on a highly technical subject. I gave it the topic, keywords to include, and the article length. It did a decent job. It still read a little "clickbaity" but was better than my worst writers but not as good as the best. Overall, it gave a good head start so that a good writer would save hours on the initial draft and just had to wordsmith the rest of the way through. By way of comparison, a good writer would prefer to start fresh than to have to wordsmith initial copy from a bad writer.

In another case, I asked a niche technical question that I already knew the answer to. The answer was astoundingly good. Consise, highly technical; correct in every meaningful way. Then I looked at the links it used to build its consensus answer and the links in four out of five cases were to my company's website's white papers. Hmmm. That's why the answer was spot on. Good I suppose... but I am not quite sure.

Finally, my CEO was beating a dead horse longstanding argument we've had. In it, he made a comparison between my business unit to one of our 90 sister companies. During the debate the CEO said "but blankety blank sells blanks all the time and they know blank-blank ahead of time, you are telling me you don't?". So I typed up his statement into the AI as "How many blanks does blankety blank sell per year?" just to get a scope for comparison. The AI replied "blankety blank does not sell blanks per se, instead they sell management services for these things. It went on to say the first one-off product in the 1950's was indeed a blank but that transition into admin and logistics. So in the end it gave me the arrow in the quiver to hold the CEO at bay (I did not win).

Draw your conclusion on this as you will.

 

[bigtiller]

"Cherish" wasn't a 70s song, it came out in the summer of 1966.

Yep, that is exactly what the A.I. said to me.
For my crowd of friends, it was a very popular song well into the 70's.

 

[CalG]

Recent commentary

https://www.wsj.com/tech/ai/how-ai-thinks-356969f8

Just like the internet, a mile wide and an inch deep.

I'm curious, how many of us feel that a "search engine", such as google, Duck Duck go, or Brave, are the same as "artificial intelligence"?

 

[paulsharvey]

Recent commentary

https://www.wsj.com/tech/ai/how-ai-thinks-356969f8

Just like the internet, a mile wide and an inch deep.

I'm curious, how many of us feel that a "search engine", such as google, Duck Duck go, or Brave, are the same as "artificial intelligence"?

Hmm, yes and no. Sure, the search engines are using it to a small degree, but its not the same. Deepseek, you can get 10 recipes for tonight, to feed a family of 5, using 3 chicken breast's, and it will give you 4 or 5 whole meals, with the recipe, cooking instructions, and a "why it works". Then, at the end of that, you can type, "We don't like cumin, or I'm allergic to peanuts", it will refine the recipes suggested.

You don't type it in Google and get list of recipes. You get a list of websites that might have recipes, and likely not what you asked for, then you search around on the web pages, to find they aren't what you wanted.

So, yesterday, not what I would call productive, more playing; i decided to try it's ability to narrow down suggestions. "What rubber worm color should work in Lake Santa Fe on large mouth bass in late spring and early summer". It suggested June bug, green watermelon, and 2 or 3 others, as well as sizes, and the Why; water is clearer than average, and those more natural colors are more visible to fish then in many of the dirtier lakes.
Yes, Lake Santa Fe is a pretty good sized lake, but Google/Yandex/Whatever isn't going to give you nearly as localized advice/or the reasons.

For the record, I do find June-bug to be the most effective color...

 

[paulsharvey]

As mentioned by someone, I dont think you want to get all philosophical with it, or ask it of rain turtles work. Ask it about rain turtles, and it's likely to suggest other folk magic to get it to rain, like nailing a snake skeleton to a tree...