Markov chains are the original language models(elijahpotter.dev)
427 points by chilipepperhott | 154 comments
A blog post by Elijah Potter explaining Markov chains as early language models and how they generate text.
#markov-chains on Hacker News
4 stories tagged markov-chains, newest first.
Show HN: I modeled the Voynich Manuscript with SBERT to test for structure(github.com)
372 points by brig90 | 123 comments
GitHub repository applying SBERT embeddings, KMeans clustering, and Markov transition analysis to the Voynich Manuscript to test for linguistic structure.
Markov chains are funnier than LLMs(emnudge.dev)
477 points by todsacerdoti | 211 comments
A blog post arguing that Markov chain text generators produce funnier output than large language models because they are less predictable.
A Baby GPT(twitter.com)
396 points by tosh | 89 comments
Tweet by Andrej Karpathy showing a tiny GPT with two tokens and context length 3 viewed as a finite state Markov chain, explaining learned transition probabilities.