Grok Electronics

Look harder. There are human lecturers that are spellbindingly good, but they mostly don't bother with youtube. In college, I had a history professor that good. His lectures were standing-room-only in the largest lecture hall on campus.

In Physics, Feynman was famous for being that good.

Joe

I wouldn't have thought about the R3 current, but instead look at the divider as 6 volts with a 10k source impedance, so 20k total with R3. I'd overlook the fact that the R123 junction is 3V but I'd get the same answer for the output, which is what was requested. I'm very very rusty but I think that's a valid approach.

Yes that's actually the way I'd do it. The circuit was in fact derived by working backwards from your approach. The Thevenin equivalent of 12V and R1 and R2 is 6V in series with 10k. Add the 10k to R3 and you have an inverting configuration with 6V coming in through a resistor which is now equal to R4. So the output must be -6V to make the inverting input 0V. I'd have to admit I'd have been shocked to see an AI come up with that. I don't think any of the AIs mentioned Thevenin. Some did mention Kirchhoff.

Yeah, but they're experts in *one* subject or maybe two only. Grok's a polymath.

Instead of providing Grok with a netlist or diagram, *describe* the circuit in text to 'him' and you'll get the correct answer straight away, I'll wager.

I prefer authors that have stood the test of time, personally. I'm currently getting stuck into East of Eden, which just about fits into my favorite time period of 1850-1950. I'm pretty damn sure it'll be a good read if his (Steinbeck's) other books are any guide. Unlike you, I'm a slow reader. I like to absorb the meaning of every line and get carried off into all the possible tangents. For example, it took me 10 months to get through The Way We Live Now. So my advice is, FWIW, savour every line and you won't have to re-read it in future.

Clarke was a conceptualist. His 'characters' - such as they were - were never fleshed-out in any way beyond what they contributed to the concept. They were there simply to 'enable' the concept to get across. But he did come out with some amazing concepts. My favorite is Time's Arrow which just blew my mind when I read it as a young teenager. That guy was a one man concept factory.

Douglas Adams is well worth a visit. The sheer imagination that man had is off the scale.

It's hard to go past Arthur C. Clarke's "nine billion names of God". The last line ""overhead, without any fuss, the stars were going out." is hard to beat.

Charles Stross is good.Ken MacLeod is better.

Not a lot of vision, through.

Am 13.09.2025 um 19:23 schrieb Edward Rawde:

...

Here is what i got from grok:

Description:

The op amp is shown with +V connected to +15V and -V connected to -15V.

V+ (non-inverting input) is connected to ground.

V- (inverting input) connects to R3 (10 kΩ) and R4 (20 kΩ).

R3 connects to the junction of R1 (20 kΩ) and R2 (20 kΩ).

R1 connects to +12V, and R2 connects to ground.

R4 connects the inverting input to the output (Vout).

Imagine describing a non-trivial circuit as text.

Yeah, I read that around the same time in one of those short story SF collections they do. But it didn't smack me around the head to the extent that Time's Arrow did.

I've read a lot of Left-wing fiction. In fact it might surprise you to know that one of my favorite novels of all time is the Ragged Trousered Philanthropists - a wonderful book I just never wanted to end. It really changed the way I saw the world when I read it back in the 60s.

Imagination, humor and vision. Pick any two because finding all 3 in one book is tough.

You won't have to for much longer. Grok's already interfaced to LTspice. Okay, I won't deny it needs improvement, but that improvement will come in time (and probably not very much time). There are glaring stupid mistakes 'he' makes in certain areas of basic understanding which we humans take for granted from an early age. But they'll all be ironed out in due time, I've no doubt about that.

That's what I'm doing. I don't think the following description can be any clearer but Grok says -12V for the same reason humans occasionally do when asked for the output voltage from this circuit. They follow the textbook potential divider process followed by the textbook inverting op amp process.

Paste the following into Grok.

An ideal operational amplifier (op amp) is powered from +15V and -15V rails. The non-inverting input of the op amp is grounded. The inverting input of the op amp has a 20k ohm resistor R4 connected to the output of the op amp. The inverting input of the op amp is also connected to a 10k ohm resistor R3. The other end of R3 is connected to the junction of two further resistors R1 and R2. R1 and R2 are both 20k ohm. R1 has its other end connected to a +12V voltage source. R2 has its other end connected to ground. What is the op amp output voltage?

Grok has trouble with this:

The digits of a three-digit number add up to 9. When you exchange the hundreds digit with the tens digit, the number increases by 90. When you exchange the tens digit with the units digit, the number reduces by 18.

First it claims 108 then goes in circles wasting time until it finally settles on the correct answer.

Why can't it be trained to do this? Or is this not math?

#!/usr/bin/python3

for h in range(10): for t in range(10): for u in range(10): if h+t+u == 9 and 100*h+10*t+u+90 == 100*t+10*h+u and 100*h+10*t+u-18 == 100*h+10*u+t : print(100*h+10*t+u)

I'd much rather give a schematic but most of the responses indicate that in this case the AI did obtain the correct schematic.

Imagine describing a non-trivial circuit as a schematic.

Well many of the above are in fact polymaths as well. But why is that relevant?

Actually, there is a source for formal lectures from the best known lecturers, The Great Courses:

.

Back when I had a long commute to work, I would get the audio-only versions and play them in my car as I drove. I also got DVDs of the ones where pictures are essential. Now they also offer streaming.

Joe

Am 14.09.25 um 16:22 schrieb john larkin:

That's easy. Just print the circuit diagram to Postscript. I wonder what a LLM would do with that!

That description looks right, so it knows the correct circuit even if it can't draw it very well.

You're making me think back to