
BREAKING: @KenBurns will join TBPN live today at 12:20p PT
Jonathan Sweeney
16 posts

@sweenejo
Economist searching for the data generating process.

BREAKING: @KenBurns will join TBPN live today at 12:20p PT

Real, non-trollish life advice: If you're a smart young person and you really want to go to graduate school, then by all means go. But if you're on the fence, probably don't. That's not where the action is. And it's not where the action is going to be for the foreseeable future.


"Fun" graph from the draft of my book. Yeah 2021 was a particularly bad year with COVID. But still not sure people realize how much of an outlier the US is in terms of lower life expectancy vs. comparable countries.

I know there are seismic movements in LLM world but I’m craving more ORM complaints on here. anyone else harboring serious love/hate of prisma? liberally running away with query_raw?



A few thoughts on how OpenAI is implementing RAG in the new Assistants Retrieval tool before I was locked out. 1. They're splitting on newlines. You can tell because they forget to insert the newlines back between the splits when giving you the reference (red squiggles). 2. The reference is contiguous. I haven't tried more complicated questions so can't rule out that they would do some kind of subquestion decomposition, but the queries I tried all just gave a single reference. 3. The number of chunks returned is variable. This indicates some kind of "small to big" strategy where they retrieve more context than they match. Perhaps something similar to our AutoMergingRetriever docs.llamaindex.ai/en/stable/exam… w/ some kind of similarity cutoff but worth a bit more investigation. 4. They have some trouble handling UTF-8. In general, very bleeding edge still, but look forward to seeing how this evolves.





JUST IN: British Prime Minister Boris Johnson has been referred to a police watchdog over his alleged relationship with an American businesswoman when he was Mayor of London. cnn.it/2nlhUmb