alt Hacker NewsI 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.
Replies
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
"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.
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