Microgpt explained interactively • Hacker News Board

Re: Microgpt explained interactively

#51

Post by sincerely » Mon, Mar 02, 2026, 7:29 PM UTC

bonoboTP wrote: post #37

UltraSane wrote: post #36

Earlier quoted context omitted.

It has gotten to the point you need timestamped keystrokes and a screen recording to prove you actually wrote something yourself.

Soon you'll be able to generate a video with AI that shows you typing the entire thing, and will narrate it in your own voice with voice cloning.

This already exists in visual art: timelapses of the drawing process were being used to prove that pictures weren’t AI generated, until someone made a program that takes a picture and generates a fake progress vid

Re: Microgpt explained interactively

#52

Post by aeve890 » Mon, Mar 02, 2026, 11:37 PM UTC

danhergir wrote: post #49

growingswe wrote: post #32

Earlier quoted context omitted.

Names is just a random problem to demonstrate the model. It could be anything, I believe

What if you just use words

Probably because names kinda obfuscate the ridiculous impracticality of this exercise. This microgpt can produce a random sequence of letters and by chance it might look like a name. If the thing output, let's say "Kianna" you just think "wow, it IS a name" but is it though? (Idk if it's a real name, at least not in Spanish) Isn't a normal word, so the randomness of names helps to hide the fact that this gpt just outputs random shit that looks like names. If you just use words you will get mostly random shit that doesn't resemble any real words. Just my hypothesis. I can see the convenience of using names. The output look like real names but you can achieve the same result with old ai and very basic algorithms.

Re: Microgpt explained interactively

#53

Post by danhergir » Tue, Mar 03, 2026, 2:40 PM UTC

aeve890 wrote: post #52

danhergir wrote: post #49

Earlier quoted context omitted.

What if you just use words

Probably because names kinda obfuscate the ridiculous impracticality of this exercise. This microgpt can produce a random sequence of letters and by chance it might look like a name. If the thing output, let's say "Kianna" you just think "wow, it IS a name" but is it though? (Idk if it's a real name, at least not in Spanish) Isn't a normal word, so the randomness of names helps to hide the fact that this gpt just out…

in other words, it works well because it doesnt make out weird names.

Re: Microgpt explained interactively

#54

Post by lozzo » Tue, Mar 03, 2026, 3:47 PM UTC

This was a beautiful article to stumble upon.

I had seen Karpathy 's work - https://karpathy.github.io/2026/02/12/microgpt/ - but found it still too demanding to get it

This was the next simplification I just needed

Re: Microgpt explained interactively

#55

Post by gwern » Tue, Mar 03, 2026, 6:28 PM UTC

gwern wrote: post #40

growingswe wrote: post #29

Earlier quoted context omitted.

I had to look up what a content mill is. I'm not one, I think. It's "random" stuff because my interests are different. These posts are not written sequentially, I've been working on them (except for this MicroGPT one) for weeks and only publishing now.

Dude, you literally start the article with > Andrej Karpathy wrote a 200-line Python script that trains and runs a GPT from scratch, with no libraries or dependencies, just pure Python . Almost immediately afterwards, you have a section titled "Numbers, not letters". Need I go on? Interestingly, despite all the AI tics, the opening passes Pangram as 100% human... though all the following sections I randomly checked a…

(Pangram commentary: https://x.com/max_spero_/status/2028620466995220568 https://x.com/max_spero_/status/2028689219112034436 )