[rock_hard]

To give you an example of the typical response quality we encountered:

@copilot can you design a low pass filter for me with 3db point of 300khz?

copilot: Sure, I can help you design a low-pass filter with a 3dB point of 300 kHz. A simple passive RC (resistor-capacitor) low-pass filter can be used for this purpose. To calculate the values of the resistor (R) and capacitor (C), you can use the following formula:

f_c = 1 / (2 pi R * C)

Where f_c is the 3dB cutoff frequency (300 kHz), R is the resistor value, and C is the capacitor value. Let's choose a standard resistor value, for example, 1 kΩ. Then, you can calculate the capacitor value as follows:

C = 1 / (2 pi R f_c) = 1 / (2 pi 1000 300000) ≈ 530.5 pF

Since 530.5 pF is not a standard capacitor value, you can use the closest standard value, which is 560 pF. With these values, the actual 3dB cutoff frequency will be approximately:

f_c = 1 / (2 pi 1000 * 560e-12) ≈ 283.5 kHz

The low-pass filter can be assembled by connecting the 1 kΩ resistor in series with the input signal, followed by the 560 pF capacitor connected to the ground. The filtered output can be taken across the capacitor. This design will give you a first-order RC low-pass filter with an actual 3dB point of approximately 283.5 kHz.

[hammyhavoc]

And how about the negative responses involving hallucination? Ideally giving an example of the worst hallucination encountered thus far and least worst thus far.

As a potential customer, I'm more interested in knowing where the potential known failure points or points of friction are than knowing what's working well.

Yes, when it works, it's certainly compelling in its responses—but as it never knows when it is wrong, it is equally compelling at a cursory glance when it hallucinates.

For most folks interested in this, their Dunning-Kruger complex will prevent them from picking up on when it's wrong because it's so convincing and sure of itself.

[nunuvit]

AI is useful for making suggestions, but you shouldn't blindly trust it like that no matter how advanced it gets. It helps you work faster, not beyond your abilities.

[hammyhavoc]

That's the thing, I'm not actually sure it does help someone work faster if everything it suggests needs to be fact-checked whilst under the guise of being always confident and never knowing it is wrong.

A lot of people liken AI to having a junior role working with you, but most junior positions have been to university and have a pretty solid understanding of a field in the first place. I wouldn't have a junior role hallucinating things that don't exist on a regular basis.

The speed of generating an output is only as meaningful as how consistently correct and appropriate that output is in terms of its value. I remain unconvinced.

[nunuvit]

If you don't do your job because you blindly accepted advice from a confident AI, a confident senior engineer, or a confident application note, then you might not have that job for much longer.

I don't know if it will make you personally work faster or not, that's your business to sort out.