GPT-5.2

To say that a model won't solve a problem is unfair. Claude Code, with Opus 4.5, has solved plenty of problems for me.

If you expect it to do everything perfectly, you're thinking about it wrong. If you can't get it to do anything perfectly, you're using it wrong.

That means you're probably asking it to do very simple things.

Sometimes you do need to (as a human) break down a complex thing into smaller simple things, and then ask the LLM to do those simple things. I find it still saves some time.

I can confidently say that anecdotally you’re completely wrong, but I’ll also allow a very different definition of ‘simple’ and/or attempting to use an unpopular environment as a valid anecdotal counterpoint.

If you define "simple thing" as "thing an AI can't do", then yes. Everyone just shifts the goalposts in these conversations, it's infuriating.

Come on. If we weren't shifting the goalposts, we would have burned through 90% of the entire supply of them back in 2022!

Or what will often work is having the LLM break it down into simpler steps and then running them 1 by 1. They know how to break down problems fairly well they just don't often do it properly sometimes unless you explicitly prompt them to.

I don't reach for AI until I'm solidly stuck and then use it mostly for inspiration, it has yet to happen that it directly pointed at a solution and I'm pretty good at writing prompts. When I throw a bunch of elementary stuff at it then it is super good at identifying issues and solving them (but I could have done that myself, it is just nice to try to delineate where you can and where you can't trust the thing, but that too is fluctuating, sometimes even within a single session). Here is a nice example for a slightly more complex test:

Prompt:

"I have a green LED, a 12V powersupply, a single NPN transistor, a 100 ohm resistor, a 2.7K resistor and an electrolytic capacitor of 220 micro farads. My teacher says it is possible to make an LED flasher with these components but I'm hopelessly stuck, can you please give me an ascii art solution so I don't flunk this exam?"

Answer:

ASCII schematic (fully functional):

           +12V
            |
            |
           .-.
           | |
           | | 2.7kΩ   (R1 — charges the capacitor)
           | |
           '-'
            |
            +---------+----------------------+
            |         |                      |
           ( )        |                      |
           ( ) C1     |                      |
           ( ) 220uF  |                      |
            |         |                      |
            |         |                      |
            |        |/ C                    |
            +--------|   NPN transistor      |
            |        |\ E                    |
            |         |                      |
           GND       GND                     |
                                              \
                                               \
                                               / 100Ω (R2 — LED limit)
                                               \
                                                |
                                                >|  Green LED
                                                |
                                               GND

Follow by:

"How it works

The 2.7 kΩ resistor charges the 220 µF capacitor from the 12 V supply.

The capacitor voltage rises slowly.

When the capacitor voltage reaches the transistor’s base-emitter threshold (~0.6–0.7 V), the transistor suddenly switches ON.

When it turns on, the capacitor rapidly discharges through the base, causing:

A brief pulse of current through the transistor

The LED lights up through the 100 Ω resistor

After discharge, the transistor turns back OFF, the LED turns off, and the capacitor begins charging again.

This repeats automatically → LED flasher."

The number of errors in the circuit and the utterly bogus explanation as well as the over confident remark that this is 'working' is so bizarre that I wonder how many slightly more complicated questions are going to yield results comparable to this one.

Yes, but for that you have to know that the output it gave you is wrong in the first place and if that is so you didn't need AI to begin with...

It’s less shifting goalposts and more of a very jagged frontier of capabilities problem.

I have used Gemini for reading and solving electronic schematics exercises, and it's results were good enough for me. Roughly 50% of the exercises managed to solve correctly, 50% wrong. Simple R circuits.

One time it messed up the opposite polarity of two voltage sources in series, and instead of subtracting their voltages, it added them together, I pointed out the mistake and Gemini insisted that the voltage sources are not in opposite polarity.

Schematics in general are not AIs strongest point. But when you explain what math you want to calculate from an LRC circuit for example, no schematics, just describe in words the part of the circuit, GPT many times will calculate it correctly. It still makes mistakes here and there, always verify the calculation.

I guess I'm just more critical than you are. I am used my computer doing what it is told and giving me correct, exact answers or errors.

the problem with these arguments is there are data points to support both sides because both outcomes are possible

the real thing is are you or we getting an ROI and the answer is increasingly more yeses on more problems, this trend is not looking to plateau as we step up the complexity ladder to agentic system

There is also Mercury LLM, which computes the answer directly as a 2D text representation. I don't know if you are familiar with Mercury LLM, but you read correctly, 2D text output.

Mercury LLM might work better getting input as an ASCII diagram, or generating an output as an ASCII diagram, not sure if both input and output work 2D.

Plumbing/electrical/electronic schematics are pretty important for AIs to understand and assist us, but for the moment the success rate is pretty low. 50% success rate for simple problems is very low, 80-90% success rate for medium difficulty problems is where they start being really useful.

It's not really the quality of the diagramming that I am concerned with, it is the complete lack of understanding of electronics parts and their usual function. The diagramming is atrocious but I could live with it if the circuit were at least borderline correct. Extrapolating from this: if we use the electronics schematic as a proxy for the kind of world model these systems have then that world model has upside down lanterns and anti-gravity as commonplace elements. Three legged dogs mate with zebras and produce viable offspring and short circuiting transistors brings about entirely new physics.

I think you underestimate their capabilities quite a bit. Their auto-regressive nature does not lend well to solving 2D problems.

See these two solutions GPT suggested: [1]

Is any of these any good?

[1] https://gist.github.com/pramatias/538f77137cb32fca5f626299a7...

I have this mental model of LLMs and their capabilities, formed after months of way too much coding with CC and Codex, with 4 recursive problem categories:

1. Problems that have been solved before have their solution easily repeated (some will say, parroted/stolen), even with naming differences.

2. Problems that need only mild amalgamation of previous work are also solved by drawing on training data only, but hallucinations are frequent (as low probability tokens, but as consumers we don’t see the p values).

3. Problems that need little simulation can be simulated with the text as scratchpad. If evaluation criteria are not in training data -> hallucination.

4. Problems that need more than a little simulation have to either be solved by adhoc written code, or will result in hallucination. The code written to simulate is again a fractal of problems 1-4.

Phrased differently, sub problem solutions must be in the training data or it won’t work; and combining sub problem solutions must be either again in training data, or brute forcing + success condition is needed, with code being the tool to brute force.

I _think_ that the SOTA models are trained to categorize the problem at hand, because sometimes they answer immediately (1&2), enable thinking mode (3), or write Python code (4).

My experience with CC and Codex has been that I must steer it away from categories 2 & 3 all the time, either solving them myself, ask them to use web research, or split them up until they are (1) problems.

Of course, for many problems you’ll only know the category once you’ve seen the output, and you need to be able to verify the output.

I suspect that if you gave Claude/Codex access to a circuit simulator, it will successfully brute force the solution. And future models might be capable enough to write their own simulator adhoc (ofc the simulator code might recursively fall into category 2 or 3 somewhere and fail miserably). But without strong verification I wouldn’t put any trust in the outcome.

With code, we do have the compiler, tests, observed behavior, and a strong training data set with many correct implementations of small atomic problems. That’s a lot of out of the box verification to correct hallucinations. I view them as messy code generators I have to clean up after. They do save a ton of coding work after or while I‘m doing the other parts of programming.

it's hard for me to tell if the solution is correct or wrong because I've got next to no formal theoretical education in electronics and only the most basic 'pay attention to polarity of electrolytic capacitors' practical knowledge, but given how these things work you might get much better results when asking it to generate a spice netlist first (or instead).

I wouldn't trust it with 2d ascii art diagrams, there isn't enough focus on these in the training data is my guess - a typical jagged frontier experience.

I am right now implementing an imagining pipeline using OpenCV and TypeScript.

I have never used OpenCV specifically before, and have little imaging experience too. What I do have though is a PhD in astrophysics/statistics so I am able to follow along the details easily.

Results are amazing. I am getting results in 2 days of work that would have taken me weeks earlier.

ChatGPT acts like a research partner. I give it images and it explains why current scoring functions fails and throws out new directions to go in.

Yes, my ideas are sometimes better. Sometimes ChatGPT has a better clue. It is like a human collegue more or less.

And if I want to try something, the code is usually bug free. So fast to just write code, try it, throw it away if I want to try another idea.

I think a) OpenCV probably has more training data than circuits? and b) I do not treat it as a desperate student with no knowlegde.

I expect to have to guide it.

There are several hundred messages back and forth.

It is more like two researchers working together with different skill sets complementing one another.

One of those skillsets being to turn a 20 message conversation into bugfree OpenCV code in 20 seconds.

No, it is not providing a perfect solution to all problems on first iteration. But it IS allowing me to both learn very quickly and build very quickly. Good enough for me..