ARC AGI v2: 17.6% -> 52.9%
SWE Verified: 76.3% -> 80%
That's pretty good!
ARC AGI v2: 17.6% -> 52.9%
SWE Verified: 76.3% -> 80%
That's pretty good!
Thus far they all fail. Code outputs don’t run, or variables aren’t captured correctly, or hallucinations are stated as factual rather than suspect or “I don’t know.”
It’s 2000’s PC gaming all over again (“gotta game the benchmark!”).
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.
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.
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..