Viewing profile — willbryk
willbryk
HN member- Joined
- Tue, May 18, 2021, 7:32 PM UTC
- HN karma
- 256
- Public activity
- 27 items
- HN profile
- View on Hacker News ↗
About willbryk
No profile information was provided.
Recent public activity
-
comment
Comment #48125748
Google is the most well known search engine, but there is very little research on how other search providers affect RL outcomes. Turns out Exa reached higher performance with 70% l…
- story
- comment
-
story
Exa-d: How to store the web in S3
exa-d is our internal data processing framework that stores the web in S3. It helps deal with the complexity of data at (web) scale using specific design decisions like declarative…
-
comment
Comment #43912479
stay tuned!
-
comment
Comment #43911323
https://exa.ai/blog/websets-evals
-
comment
Comment #43909789
Thanks Artem! That makes sense to specialize for the biggest customers. Yes, a lot of problems in the world would be improved by better search, including dating.
-
comment
Comment #43909670
This might be possible if you specify geospatial location as an enriched column. The visualization of it as a map though is not supported in the UI, but can be built by giving an L…
-
comment
Comment #43909638
Because Google makes money from ads, they're not actually optimized to build the best general search engine in the world, they're optimized to build the search engine that makes th…
-
comment
Comment #43908986
There aren't currently any vision LLMs involved. But if you asked for image links, it'd probably find you something!
-
comment
Comment #43908907
Thanks for letting us know - made a Linear ticket
-
comment
Comment #43908841
Mission of Exa has always been to build much better web search. The evolution has been: - 2022: Consumer-facing embeddings search (back when we were known as Metaphor) - 2023: Web …
-
comment
Comment #43907973
Thanks for the support - we're getting hug of death though so please bear with us while we scale up!
-
comment
Comment #43907853
Yup exactly! And we expose this as a regular search API as well as in the Websets product.
-
comment
Comment #43907847
Thanks for the feedback! Yeah we'd love to make the product as accessible and cheap as possible, but as of state of AI costs of 2025, it's a very expensive product to run and so we…
-
comment
Comment #43907816
Hm! I'll try this out. Sometimes info like price are hard to parse out because the data may be on ecommerce-style websites that have many crawling protections
- comment
-
comment
Comment #43907781
Thanks! Let us know how you find it :)
-
comment
Comment #43907768
By cruft cleaner, do you mean cleaning the HTML well? Right now, we do 2 things to help with that, a pretty robust parsing stack as well as a "summaries" feature that returns an LL…
-
comment
Comment #43907722
Thanks!
-
comment
Comment #43907711
Not a pivot - Websets is just a new product! Mission of Exa has always been to build much better web search. The evolution has been: - 2022: Consumer-facing embeddings search (back…
-
comment
Comment #43907634
We're a startup, so most of our resources go towards use cases that our users care most about. So the search should work best for - people, companies, papers, high quality written …
-
comment
Comment #43907139
We render JS and then parse pages, but that process will definitely parse out Adobe Analytics tags unfortunately. Noting this though!
-
story
Launch HN: Exa (YC S21) – The web as a database
Hey HN! We’re Will and Jeff from Exa ( https://exa.ai ). We recently launched Exa Websets, an embeddings-powered search engine designed to return exactly what you’re asking for. Yo…
-
story
Show HN: Exa (YC S21) – embeddings search agent with >20x recall than Google
Hey HN! I'm Will, founder of Exa (YC21 - https://exa.ai ). Today we're opening up Websets, a search engine that finds massive lists of correct results given complex queries. For ex…