Viewing profile — supo
supo
HN member- Joined
- Fri, Apr 27, 2012, 10:59 AM UTC
- HN karma
- 349
- Public activity
- 89 items
- HN profile
- View on Hacker News ↗
About supo
Hit me up on x.com/svonava
Recent public activity
-
comment
Comment #48902287
The environment allows for separation of the useful good ones from the "only in it for the cash" ex-investment banking types ^_^
- story
-
story
Show HN: Distributed LLM tracing and GH PR/issue linking [Apache 2.0]
See where coding agents struggle, what tools eat tokens and how it all links to GitHub PRs & issues. I open-sourced a tool that streams data from all your dev machines, VMs & sandb…
-
comment
Comment #48137842
Open-source k8s cluster for serving a wide catalog of small language models across search, OCR & data processing.
- story
-
comment
Comment #44082092
by that same logic, why would you not strive to push all the signals you have available into the ANN search? sure, some will have reduced resolution vs using a heavy reranker, but …
-
comment
Comment #44082053
one thing to remember is that bm25 is purely in the domain of text - the moment any other signal enters in the picture (and it ~always does in sufficiently important systems), bm25…
-
comment
Comment #44078114
Here is a quick overview, doesn't really explain the deep details though: https://www.youtube.com/watch?v=ikYsr6nvbdE Basically think mixture of experts, but each expert is an enco…
-
comment
Comment #44078083
This article focuses on ways to make "pre-fetching" more accurate, reducing or eliminating the need for reranking to improve latency/cost but also sometimes quality - for example i…
-
comment
Comment #44078073
If this was a solved problem, every e-com website would already run some variant of https://arxiv.org/pdf/2209.07663 for all their shopping surfaces and some version of "deep resea…
-
comment
Comment #44078043
It allows faster experimentation because you can't do things like partial embedding updates and reasonable schema migrations on your vector search index - if you could, you'd exper…
-
comment
Comment #44078021
If you could wave a magic wand and push all the ranking signals into retrieval and that index would be fast to update and not that expensive to operate - you would do that and you …
-
comment
Comment #42404665
We are mostly focused on natural language search in e-commerce/marketplace/travel settings right now. There we have a production deployment that drove $15M of incremental revenue t…
-
comment
Comment #42404654
We focus on text, images, numerical, categorical and timestamp-properties for the objects you vectorize with Superlinked. The performance will depend on which models you chose to u…
-
comment
Comment #42404642
Supported VDBs: Currently MongoDB, Redis Search and Qdrant https://docs.superlinked.com/run-in-production/index-1 As you say, AstraDB also offers vector search (you can see it at h…
-
story
Show HN: Superlinked – Vector Embeddings for Structured and Unstructured Data
Hi HN, I'm Daniel from Superlinked! We have built an open-source framework that improves vector search relevance and usefulness by combining structured metadata with unstructured d…
-
comment
Comment #39027028
A table comparing the features available with different vector databases. The project is open-source and developed by a community of practitioners with points of contact from the d…
- story
-
comment
Comment #34705698
And you decided to not work remotely and 10x your income instantly, because you'd miss your office and colleagues. Got it!
-
comment
Comment #34428730
Any apps that can benefit from social interactions. A good example is DuoLingo. They built a social+ product for learning languages, have 50m MAUs and $250M revenue!! There are tho…
- story
- story
- story
-
comment
Comment #21807313
The removal of barriers favors those who can take advantage of the newly acquired access and information. Your life reflects this capacity as much as the environment that let it ma…
- story