Torsten Bøgh Köster (@[email protected])
3.3K posts
@tboeghk
Freelancer Search & Operations. Builds #Kubernetes and #observability stacks both on-premise and in the cloud, @ApacheSolr nerd, @stmhamburg organizer
I used to agree with this, but have changed my mind On most teams infra folks aren't MLEs. They specialize in rock-solid L0 retrieval at high scale. A worst case L0 fallback that has "one dumb job". Its harder to do that with one system that "does everything"
I've been taking a break from work for the last few weeks, so missed much of the brouhaha over the McKinsey developer productivity article. But I'm sure that I could not write a better response than this one from @tastapod dannorth.net/mckinsey-revie…
tinyvector - the tiny, least-dumb, speedy vector embedding database. pretty much: you don't need complicated algos, just brute force nearest neighbors. pre-launching this project + why i'm building this:
At #bbuzz this year, @tboeghk & Dennis Berger will discuss how to tackle large search results by estimating hit count, interpolating a first phase ranking & limiting the returned result set to the most relevant documents in a multi-million document index. 2023.berlinbuzzwords.de/sessions/?id=K…
