AI being helpful thread

[paulsharvey]

I could Easily see a time soon, that every student is assigned an AI teaching assistant, that teaches to each students own specific learning trends. We all had certain teachers that we connected with, and their style helped us learn, and others that though using basketball examples, or whatever. I learned to read without sounding words out, just naturally; others they tried to teach that way, but they needed phonics. Yes, teachers will still be around, largely as class room bouncers, but in a room with 24 students, no one can teach optimally to each one.


Some of us think better with picture, some with numbers, somw with words. Heck, some people's brains tell them what words to use, and others of us are just as surprised as you by what comes out of our mouths. Brains are complex, but AI can tailor to 1000 brain types

 

[DarkBlack]

No, it's not. It's autonomous. You might want to read up on it.

I disagree. Autonomous is autonomous. That technology has been around a long time. It’s not true AI

 

[MossRoad]

I disagree. Autonomous is autonomous. That technology has been around a long time. It’s not true AI

Read the articles.

 

[scootr]

I ask AI of that is AI


"Not necessarily.


A “robotic arm that lays bricks” could be:

1. Just automation (not really AI)
   If it:
   • Follows a fixed, pre-programmed path
   • Assumes everything is exactly where the plan says it is
   • Uses simple sensors (limit switches, encoders) only to avoid collisions or detect end-stops
   • Does not “interpret” its environment or adapt beyond basic error checks
   • Then it’s basically robotic automation or CNC-style control, not what most people mean by AI.
2. AI-driven robotics
   It becomes AI (or at least uses AI techniques) if it does things like:
   • Computer vision: recognizing bricks, mortar lines, walls, and adjusting placement from camera images
   • Perception + planning: dynamically planning where and how to place each brick based on real-world measurements, not just a fixed program
   • Learning/improvement: improving placement speed or accuracy over time from data (machine learning / reinforcement learning)
   • Adapting to variation: handling crooked foundations, slight brick variations, or obstacles without a human reprogramming every detail
3. Why the confusion?
   • Many industrial robots are marketed as “AI” even when they are mostly traditional automation with some advanced sensors.
   • Technically, AI is about making decisions under uncertainty using data. If the bricklaying arm is doing that, it’s using AI. If it’s just repeating a pre-planned motion, it’s “just” a robot.

So:

• A robotic arm that lays bricks is always robotics.
• It is only AI if its control system includes perception, learning, or intelligent decision-making, not just fixed motion control.

 

[MossRoad]

I ask AI of that is AI


"Not necessarily.


A “robotic arm that lays bricks” could be:

1. Just automation (not really AI)
   If it:
   • Follows a fixed, pre-programmed path
   • Assumes everything is exactly where the plan says it is
   • Uses simple sensors (limit switches, encoders) only to avoid collisions or detect end-stops
   • Does not “interpret” its environment or adapt beyond basic error checks
   • Then it’s basically robotic automation or CNC-style control, not what most people mean by AI.
2. AI-driven robotics
   It becomes AI (or at least uses AI techniques) if it does things like:
   • Computer vision: recognizing bricks, mortar lines, walls, and adjusting placement from camera images
   • Perception + planning: dynamically planning where and how to place each brick based on real-world measurements, not just a fixed program
   • Learning/improvement: improving placement speed or accuracy over time from data (machine learning / reinforcement learning)
   • Adapting to variation: handling crooked foundations, slight brick variations, or obstacles without a human reprogramming every detail
3. Why the confusion?
   • Many industrial robots are marketed as “AI” even when they are mostly traditional automation with some advanced sensors.
   • Technically, AI is about making decisions under uncertainty using data. If the bricklaying arm is doing that, it’s using AI. If it’s just repeating a pre-planned motion, it’s “just” a robot.

So:

• A robotic arm that lays bricks is always robotics.
• It is only AI if its control system includes perception, learning, or intelligent decision-making, not just fixed motion control.

It's using AI to make decisions.

 

[DarkBlack]

Read the articles.

There’s the universe of opinions on what constitutes AI. I just watched a video, and the “expert” there claimed AI started back in BC
He counted every single thing that was ever invented related to computation, as AI.

Me personally, when I say AI, I’m talking about the most recent developments in the last few years of programs, that can actually modify/ write, their own code.
This is a huge difference over traditional software that only appears smart, because sensors and read/writes to databases.

For a program to be able to change its own code, means it has the ability to evolve endlessly without the initial human restrictions.
As sci-fi movies have portrayed, that program is true AI, and could modify itself, to be self aware.
That’s in a whole different league

 

[EscapedSuburbia]

One "trade" that should worry, Translators. I have seen some incredible stuff that auto translates live speak to most major languages. Obviously it still needs improvement as Mexican Spanish isnt the same as Puerto Rican Spanish, or Old world Spanish, but if you make a living as the Sign Language lady at a public meeting, id start learning another skill, as thats Easy to replace with AI, and do a better job, for a fraction of the cost

A friend of mine in his mid-70s recently married a lady from Peru. He doesn't speak a word of Spanish and has no interest in learning. She's working on her English but it's still marginal. Most of their communication is through a translation app on their phones. What's nice is there's no typing involved. The phone listens to the conversation and translates automatically and either prints it out or speaks it. Automatic translation has come a LONG way.

Before I retired I used to work a lot in Poland. I could point my phone's camera at something like a sign or vending machine and it would translate the entire thing to English and overlay it on the camera image. For example, point it at a soda machine and I'd still be seeing the soda machine on my phone's screen but all the text would be translated in the image. It was amazing.

 

[DarkBlack]

 

[EscapedSuburbia]

This is a good example of why experts are predicting an AI market bubble. Companies like this co-opting the term "AI" in their marketing when in reality it's just standard automation. It's an industrial robot with vision guidance and proximity sensors - pretty standard stuff. The problem is investors are dumping huge sums into these companies because of the misappropriation of the term AI.

Before retiring in 2021 I was an engineer in the factory automation field and did robot and vision system integration. AI is just now starting to be applied to vision systems and it eventually will be a game changer but it's not there yet. Humans are amazing at identifying things, especially defects. Current vision systems can only identify defects that are specifically trained and when you're building a machine for a new product it's hard to get realistic defects for training the system. You end up intentionally creating defects but they're rarely the same as ones that occur naturally. And there are always defect types you didn't consider so they don't get trained into the vision system. AI will eventually tackle this and it will make life a lot easier for the engineers and technicians who maintain machines with vision. Tweaking vision is a frustrating, non-stop job in factories.

 

[JeepHead]

This is a good example of why experts are predicting an AI market bubble. Companies like this co-opting the term "AI" in their marketing when in reality it's just standard automation. It's an industrial robot with vision guidance and proximity sensors - pretty standard stuff. The problem is investors are dumping huge sums into these companies because of the misappropriation of the term AI.

Before retiring in 2021 I was an engineer in the factory automation field and did robot and vision system integration. AI is just now starting to be applied to vision systems and it eventually will be a game changer but it's not there yet. Humans are amazing at identifying things, especially defects. Current vision systems can only identify defects that are specifically trained and when you're building a machine for a new product it's hard to get realistic defects for training the system. You end up intentionally creating defects but they're rarely the same as ones that occur naturally. And there are always defect types you didn't consider so they don't get trained into the vision system. AI will eventually tackle this and it will make life a lot easier for the engineers and technicians who maintain machines with vision. Tweaking vision is a frustrating, non-stop job in factories.

You would think it would be simpler to train it what it SHOULD look like and to notice when there is a difference.