Live data from Hacker News

Markov Chains are the Original Language Models

elijahpotter.dev

1–10 of 177 posts

Re: Markov Chains are the Original Language Models

#3
Markov chains were one of the coolest discoveries of my programming career and I spent years using them to make forum and social media bots trained on people’s post histories for them.

I think that experience is part of why I’ve been generally unimpressed with a lot of LLM hype. Like yeah, it’s cool and definitely more useful than a markov chain - but for the amount of resources that went into it I’d expect the gap to be quite a bit larger than it really is.

Re: Markov Chains are the Original Language Models

#5
post #4

Markov Chains are cool stuff. Back in 2015 in one of my senior class projects, I built a haiku bot that would take a seed word and make a haiku from a corpus of Tweets I collected from the firehose API.

Intriguing. How did you get it to fit the syllable count?

Re: Markov Chains are the Original Language Models

#10

This is what I've been saying to people, LLMs aren't much smarter than a Markov Chain - a lot of twitter bots and earlier chat agents were driven by them. What I do see though is the infrastructure around LLMs making a difference.

>This is what I've been saying to people, LLMs aren't much smarter than a Markov Chain

They're based on the same principles, but extend quite beyond that, and are way smarter than Markov Chains.

So, it's not just the infrastructure that's makes the difference (if they were only as effective as Markov Chains, then having the same or even more infrastructure wouldn't make any difference).

Post reply on HN