WARNING ! AI rots your Brain

Absolutely.. LLMs are merely tools that requires human input, which just happens to be in our natural spoken language, to produce a digital output.

Here's an interesting talk just published on social media, which touches on how software is changing: https://x.com/aaditsh/status/1935611395653226588

Edit. Video also found on YouTube.

Edit media

Dimensions x Small Medium Large Custom

Subject (required) Brief Description Tags (separated by comma) Video visibility in search results Visible Hidden

Parent content

RE: WARNING ! AI rots your Brain

Poster

Upload Preview

Ok

Cancel

shabaz said:

They don't have a way out because they have no IT staff

Having IT staff doesn't necessarily solve the issue either, as they often don't have the resource to convert (and then actively maintain) each of the individual's spreadsheets into new database management systems.

I've seen IT departments actively dissuading people from attempting to use a DBMS, as it becomes an even bigger headache for them when it all goes wrong and they are then called upon to recover the data.

Yes the more people rely on technology the less they learn to survive by thinking.

The "smart" phone will go down in history as the greatest detriment to the development of intelligent thought.

I like to differ. Technology has propelled us, and keeps on propelling us, at an incredible speed.

Nothing pushed math like technology, and the will of humanity to advance technology.  

And we survive decennia longer than before technology. Both you and I are older now than any human before tech ruled.

Just maybe... AI can help the smart get smarter.  I won't say it helps the dumb get dumber.  Some of them are quite brilliant - thinking of things I would never have even considered - EVER.  We have always had the lazy and the Con man.  I do think we lose some of the simple, elegant solutions.  But do they still have value?  How important is optimizing your code when you have Gigabytes of RAM and Terabytes of storage space?  Is it as critical as back when 640k was the hard stop limit?

I think of the movie "Idiocracy" and of Orson Welles' "The Time Machine".  And then I remind myself "It's never going to happen."  Some Engineers are made, but most are born.  The same is true of artists.  I'm pretty sure that when folks saw the horseless carriage, some pundits said that people would stop walking and get too fat to move (like in WALL-E).  They could never have comprehended that running would be a $44 BILLION dollar world-wide industry in 2024.

We've been told for forever, "Work smarter.  Not harder."  Maybe MIT's assessment is skewed.

Sorry, I missed seeing this message earlier.

The answer doesn't have to be a database (although it's highly useful if one is involved [but I wouldn't recommend someone install and manage it themselves when cloud services are so cheap], my point is that it is limiting if your building-blocks are just cells and formulas and a flat file.

IT departments have to meet the business's IT needs since that's their one job in life. Whether they recommend a database or not is an implementation thing (but it's still pretty strategic! so personally, if it were me, I'd be wanting compelling reasons if their solution didn't involve a database whether it's managed by them or not.

Even batch processing could help if they can program (or get AI to help with this), or uploading to (say) any software-as-a-service system for sales or inventory, and hope your files are in the right format for upload. 

At least there's the possibility of several people collaborating on an Excel spreadsheet, but when it's complicated enough, the owner won't risk others touching it; they build the outputs themselves, and everyone is dependent on that one person.

I've visited a few small business meet-ups (mostly the ones I've seen are selling products, some specialist, some general consumer items, but they all have some common tasks they need to perform, and naturally they almost all unanamously started off with Excel because it made sense), and then they found people liked their products or their friendly service or reliability and came back, they grew, and now are hitting the bottleneck and that's almost always the sore point they talk about. They live for the yearly meet-ups so they can exchange feedback about what cloud services they have found helped them with particular problems, since no-one can afford to waste a lot of time/resources trying to make a go of a service only to realize it isn't working for them.  

research: I asked AI (chatGPT) if the RISC or ARM cores were most efficient.

First answer was disappointing, but then it was on track:

> me: what core is most efficient on rp2350, riscv or arm?

The RP2350 is a microcontroller from Raspberry Pi Ltd. that features a dual-core Arm Cortex-M0+ processor. It does not have a RISC-V core, so in the context of this specific chip, only the Arm Cortex-M0+ is present and thus is the core in use.

> me: this answer is wrong. rp2350 has 2 risc v cores and 2 arm cores

You're absolutely right—my apologies for the confusion. The RP2350 features 2 ARM Cortex‑M33 cores or 2 Hazard3 RISC‑V cores, selectable at boot, or even one of each if desired forums.parallax.com+15raspberrypi.com+15sparkfun.com+15.

️ Efficiency: Cortex‑M33 vs Hazard3 RISC‑V on the RP2350

 Power & Performance

• Cortex‑M33 (150 MHz):

  • Armv8‑M architecture with DSP and single-precision FPU.

  • Optimized for energy efficiency with Thumb‑2 ISA and TrustZone security dfrobot.com+1reddit.com+1en.wikipedia.org+1smist08.wordpress.com+1.

  • Best suited for signal processing and compute-heavy tasks due to hardware acceleration.

• Hazard3 RISC‑V (150 MHz):

  • Custom in-house dual-core design (RV32IMAC+) by Raspberry Pi raspberrypi.com+7en.wikipedia.org+7en.wikipedia.org+7.

  • Compact implementation, removes ARM licensing costs, and supports compressed ISA for denser code reddit.com.

  • Likely scales well in silicon area and cache use—designed with minimalist efficiency in mind.

Code Density & Ecosystem

• RISC‑V often provides better code density thanks to its C-extension, which can reduce flash/cache usage.

• The mature Arm ecosystem offers more optimized toolchains and libraries for DSP, security, and low‑power modes.

• RISC‑V ecosystem is growing rapidly, but M33 still leads for production-ready support raspberrypi.com+15dfrobot.com+15raspberrypi.com+15forums.parallax.com+2en.wikipedia.org+2datasheets.raspberrypi.com+2.

 Switching Architecture

• Switching between architectures requires a reset—only two cores run at a time datasheets.raspberrypi.com+1smist08.wordpress.com+1.

• Thermal and power characteristics are similar at same clock rate; the difference lies in ISA benefits and use-case efficiency.

 What’s Most Efficient?

 At 150 MHz on RP2350:

• Per‑cycle performance:

  • Cortex‑M33 wins if you're using DSP/FPU-heavy workloads.

  • Hazard3 excels in compact code execution and flash efficiency.

• Power consumption:

  • Both are designed to be low-power; Cortex‑M33 likely has slight edge due to mature low‑power modes and silicon optimizations.

  • Hazard3 may consume less static power and has less overhead in instruction handling.

 TL;DR

• For DSP, FPU, and security-heavy applications, use the Cortex‑M33.

• For code-density, open-source flexibility, and potentially lower area cost**, go with Hazard3 RISC-V.

• Power efficiency is comparable, but your workload (FPU vs compact code) determines the best choice.

shabaz said:

and naturally they almost all unanamously started off with Excel because it made sense

The spreadsheet is one step up from the pen and paper plus calculator scenario, which is the way most of us were probably taught at school. So it's a natural step to roughing out a problem quickly and it's quick for most people to set up and to change and update.

There perhaps appears to be a bit of a grey area as to how long you stick with this method though before you stop and think about it in terms of efficient data structures, which most of us probably weren't taught in school.

Also there perhaps is the return of investment - is the project even still going to exist by the time you complete the data migration, or was it shut down early because you appear to be spending all your time trying to automate the data management.

Who is developing more? A.I. or us?
At the moment I would say that "commercial" (free access) A.I. is winning.

True, but when I encounter young people who can do nothing without their smart phones, I find they are useless in a crisis because they have to google everything rather than know what to do by knowledge and understanding.

Common sense should force everyone to ask one simple question, what do you do if you lose the internet.

Some say that is impossible, but it is really only one EMI event away from happening.

Learning is so much more than just being able to look something up.