[allthatineed]

I remember playing with megahal eggdrop bots.

This was one of my first forays into modifying c code, trying to figure out why 350mb seemed to be the biggest brain size (32 bit memory limits and requiring a contiguous block for the entire brain).

I miss the innocence of those days. Just being a teen, tinkering with things i didn't understand.

[vunderba]

I remember reading the source of the original MegaHAL program when I was younger - one of the tricks that made it stand out (particularly in the Loebner competitions [1]) was that it used both a backwards and forwards Markov chain to generate responses.

[1] https://en.wikipedia.org/wiki/Loebner_Prize

[foobarian]

I'm old now, but thanks to LLMs I can now again tinker with things I don't understand :-)

[jcynix]

The nice thing about LLMs is that they can explain stuff so you can learn to understand. And they are very patient.

For example I'm currently relearning various ImageMagick details and thanks to their explanations now understand things that I cut/copy/pasted a long time ago without always understanding why things worked the way they did.

[codr7]

Are you though? Or is the LLM the target of your tinkering and lack of understanding? Honest question.

[anthk]

Hailo it's still alive under CPAN.