Viewing profile — jeffreyw128

This was my favorite course in college!

This is cool! If you want to add embeddings over internet as a source, you should try out exa.ai. Includes: wikipedia, tens of thousands of news feeds, Github, 70M+ papers includin…

Hey Paulista, Cofounder Jeff here. Both!

Exa | San Francisco | In person | Full time | $130K-350K Jeff, cofounder of Exa.ai here. LLMs represent a brand new opportunity to organize humanity's knowledge, in a way that hasn…

Exa | San Francisco | In person | Full time | $130K-350K Jeff, cofounder of Exa.ai here. LLMs represent a brand new opportunity to organize humanity's knowledge. We're an AI resear…

Exa | San Francisco | In person | Full time | $130K-180K Jeff, cofounder of Exa here. LLMs represent a brand new opportunity to organize humanity's knowledge, in a way that hasn't …

Missed exa.ai! Embeddings-based search engine with its own index

Exa | San Francisco | In person | Full time | $130K-180K Jeff, cofounder of Exa here. LLMs represent a brand new opportunity to organize humanity's knowledge, in a way that hasn't …

That's true. Although should be much harder

Do our best at getting the right content. For paywalls/login - we play pretty straight, always obey robots.txt, etc.

Yup, definitely still gameable but if the model learns what high quality content is like and what high quality webpages there are (which it does), then the only way to game would b…

The issue with traditional search engines is that keyword-first algorithms are extremely gameable. Try https://search.metaphor.systems - it's fully neural embeddings-based search. …

This is the dumbest thing I've read in a long time

Check out http://metaphor.systems/ - neural embeddings based search that is really good at finding the longtail of high quality content. Really good for finding personal pages, nic…

It’s especially terrifying that misinformation compounds multiplicatively with AI because it happens in 2 layers - once at the retrieval layer (where AI-generated content is worsen…

Hey HN! We wrote a blog post about our adventures in building a (neural) search engine in the post-LLM world. We hope it gives a perspective on how we're thinking about the future …