Profile avatar
vickiboykis.com
ML Engineering. LLMs 😬. Information retrieval. Infra. Systems. Normcore code. Nutella. Vectors. Words. Vibes. Bad puns (soon). https://vickiboykis.com/what_are_embeddings/
2,465 posts 37,482 followers 890 following
Regular Contributor
Active Commenter

if the cache is so good why don’t they make the whole app out of cache

Still thinking about this fantastic post by @vickiboykis.com on the wide-ranging impacts of regularly reading HN. 🧪 It really is one of the most underused resources in tech. Vicki captures it well: it’s “the perfect ambient watercooler to be near senior technically excellent people in the industry”

scala alt account

Tech people have laptop stickers of laughing pizza slices and upside down smileys and inside is like the most gnarled async code holding up a distributed system for 10 million users

If the data is not uniformly distributed on Riemannian manifold I don’t even want to hear it

👑🐐 news.ycombinator.com/item?id=4389...

There is a kind of magic that comes from a point in a codebase where you and the other people are in sync and are moving over the same contextual space of the problem area.

Redis is open source again: antirez.com/news/151

big QOL lift for me: fun_black_box = get_black_box() fun_black_box: dict[str, list[str]] = get_black_box()

The more experience I get, the harder it feels to blog with confidence

if you are using primarily local models, which ones are you using and for what lately?

I love opening up the next Jira ticket and finding no requirements and then getting real mad at the person who created it (me)

Yeah decreasing time complexity, flattening code, adding cache, etc etc, but it’s wild how much one well-written log statement can improve the codebase.

I’ve never regretted writing documentation but I’ve regretted not writing it.

The slightly concerning/brittle era of LLMs in IR 😅 #ECIR2025

This is so incredibly cool. Embeddings are lingua franca for so many retrieval/LLM/recommendations use-cases and I really enjoyed working with embeddings in Redis via the search module, can’t wait to try this.

Love this endler.dev/2025/best-pr...

Docker is doing local LLMs 👀 www.youtube.com/live/mk_2MIW...

To experiment with multi-agent systems you either need a clear business case and big budget, or you need to be a jabroni with a high credit limit. I'm just the jabroni for the job, so I taught Claude to play chess, and learned a ton along the way: jfkirk.github.io/posts/claude...

Sir Isaac Newton didn't have to spend this much time managing package dependencies

can’t even let the old neurons rot for 20 min on insta

quick new post on what i've gotten out of HN vickiboykis.com/2025/03/17/2...