> Our goal continues to be building the best LLM engineering platform
Interesting headline for a checks notes time series database company.
Interesting headline for a checks notes time series database company.
[0] https://clickhouse.com/blog/clickhouse-acquires-langfuse-ope...
Disclosure: I run Altinity, a vendor in this space.
(Update: Disclaimer -> Disclosure. Sigh.)
always nice to see a database ceo be "one of us" and/or "write like a real human being".
(they've never been a time series database company either lol)
It’s great when you get this insight as a student of NLP, because suddenly your toolset grows quite a bit.
E.g, fitting a model to house prices, you don’t care if feature 1 is square meters and feature 2 is time on market, or vice versa, but in a time series, your model changes if you reverse the order of features.
With text, the meaning of word 2 is dependent on the meaning of word 1. With stock prices, you expect the price at time 2 to be dependent on time 1.
Text can be modeled as a time series.
A language model tells you the next character/token/word depending on the previous input.
Language models are time series.
It’s not an audacious claim.
Any student of nlp should have met a paper modeling text as time series before writing their thesis. How could you not meet that?
RAG and vector Approximate Nearest Neighbour (ANN) is the the go to use case.
[2] https://arxiv.org/abs/2506.02389
[3] https://arxiv.org/html/2402.10835v3
Some links from the top of Google search.
Take a look here, also, it's an important law: https://en.wikipedia.org/wiki/Benford%27s_law
It is possible for LLMs to learn Bernford's law, implicitly. So they will be non-null predictors of time series data, because time series data is also Bernford-law-distributed [4].
[4] https://ui.adsabs.harvard.edu/abs/2017EGUGA..19.2950T/abstra...