Why “perplexity” is being discussed
The most recent Hacker News stories and comments contributing to this topic's mentions.
Perplexity is not defined in the article. FYI: Perplexity is the degree of surprise the model has in predicting the next token, given a sequence of tokens. At the worst case, pe…
by hazrmard · Nov 22, 2026
Very interesting article. I'm someone who has no ML background but tries to keep in touch with what's happening in the inner world of LLM training. For those not familiar with p…
by FailMore · Nov 22, 2026
You're right. If they really wanted to address the problem of coordination, then they would look at better measures like MDL. The cynical part of me thinks that the main reason…
by nsagent · Nov 22, 2026
It seems like perplexity would also be a function of the composition of the training set. If the training set is high quality and therefore fundamentally more predictable, then…
by zmmmmm · Nov 22, 2026
I, too, can make a chart of perplexity drops
by seizethecheese · Nov 22, 2026 · 2 points
I can figure out how an ant thinks. But unless I am trying to do it on purpose, I won't copy an ant. What I’ll do when I'm hungry is a different question. Transforming your anal…
by LudwigNagasena · Nov 22, 2026
Interest
Proportion of Hacker News items mentioning "perplexity" over time.
Mentions
Total number of Hacker News items mentioning "perplexity" over time.
In information theory, perplexity is a measurement of how well a probability distribution or probability model predicts a sample. It may be used to compare probability models. A low perplexity indicates the probability distribution is good at predicting the sample. Read more on Wikipedia