My article is an architecture breakdown of how Exa AI built web search that's better than Google — and what is the bare minimum cost to build web scale search today with napkin math.
Please check it out if you're curious about:
- How modern AI search engines like Exa, Perplexity, and Parallel Web Systems operate under the hood.
- Learning napkin math style estimation (technique popularized by legends like Jeff Dean)
- How vector compression tricks like matryoshka embeddings + binary quantization change the economics of billion scale search
Please take my estimates with a grain of salt since my goal is to just get in the right ballpark. Also feel free to comment/DM if you see any wrong or suboptimal assumptions :)
Hi, I built a cool tool that can help you find the next movie, song, book, etc that's actually worth trying.
You can ask:
- Movies like Harry Potter
- Novels in mystery genre with a female protagonist
- Songs to feel good after breakup
- Authors like Yuval Noah Harari
- Video games like GTA
- And so much more :D
I'm building a job board exclusively for open source companies like Gitlab, HuggingFace, Gitpod, Sentry, etc. Please follow the twitter handle to stay updated about the MVP launch :)
It will take significant amount of effort to curate and go through such articles/resources. If I can also get paid for it, it would be better(than not getting paid).
But you've reminded me that it's possible to not charge and use sponsorship to earn revenue. I prefer doing that :) (Win-win for everyone)
Hi, I totally agree with you that nobody would pay for tracking their time. Infact, a lot of free tools are already available to do the same. People know when they're wasting time and often want to (because of boredom). I'm just wondering if it's possible to build tools that can help people take decisions ahead of time which changes their behaviour (maybe with a little bit of properly designed gamification). Thoughts ?
iPhone yea, I don't recall any configuration, I just get a weekly notification about screen type broken down by app category, app, and usage percentage change form the prior week.
Please check it out if you're curious about: - How modern AI search engines like Exa, Perplexity, and Parallel Web Systems operate under the hood. - Learning napkin math style estimation (technique popularized by legends like Jeff Dean) - How vector compression tricks like matryoshka embeddings + binary quantization change the economics of billion scale search
Please take my estimates with a grain of salt since my goal is to just get in the right ballpark. Also feel free to comment/DM if you see any wrong or suboptimal assumptions :)