Jesse Steinweg-Woods retweeted
Finally, someone did it. Python for React.
React is the most popular front-end framework used to build interfaces and now all python devs can use it.
This means you can code an ML model, develop a backend and design a front end all in one language.
github.com/reactive-python/r…
Jesse Steinweg-Woods retweeted
Stop using only ChatGPT.
I don't understand why people don't use Chrome AI extensions.
Here are insane AI Chrome extensions to save hours of work:
Jesse Steinweg-Woods retweeted
Haystack is such a slick framework for out of the box semantic search w transformer, vector index integration. Joined the @deepset_ai office hours this week, team is really on the ball. Wish we had this when we were building @SkipFlag. cc @peteskomoroch
github.com/deepset-ai/haysta…
Jesse Steinweg-Woods retweeted
I just wrote a bit about what I'm working on and why I'm excited about it: erikbern.com/2022/12/07/what…
Jesse Steinweg-Woods retweeted
Is it that we need more end to end tools like a plug-in to elastic search that “just works” out the box? Is it infra? Or is the marginal benefit smaller than I think it is?
I know some companies are using it, it’s just not as widespread as I expected it to be by now.
Jesse Steinweg-Woods retweeted
A theory I have about product development is that you can totally do gradient descent all the time and build a really good product! The main reason teams that get stuck in a “local maxima” is that they believe that every change has to be a Pareto improvement.
Jesse Steinweg-Woods retweeted
A lot has been speculated about TikTok's recommendations. This is the first paper I've read by the team, and it has many interesting details: expirable embeddings, parameter server, online training... Good #recsys stuff arxiv.org/abs/2209.07663
Jesse Steinweg-Woods retweeted
RecSys 2022 was a blast! Here's a recap with three of my favorite papers and more than a dozen summaries.
Did I miss any key papers? Please comment below!
#RecSys2022
eugeneyan.com/writing/recsys…
Jesse Steinweg-Woods retweeted
Interesting work by Amazon search “On the Value of Behavioral Representations for Dense Retrieval" 🧵
arxiv.org/pdf/2208.05663.pdf
Jesse Steinweg-Woods retweeted
Stumbled upon this neat flowchart for choosing text classification methods. I usually eye-balled it, but using a samples/number ratio cut-off seems reasonable. I.e., with a samples/number < 1500 use a bag-of-words model, with a >= 1500, use a seq. model (developers.google.com/machin…)
Jesse Steinweg-Woods retweeted
My editors just shared with me the feedback from early reviewers and I'm in tears 😭
With the help of so many people, I worked really hard on this book. I'm grateful that people gave it a chance.
Read the book online: learning.oreilly.com/library…
Pre-order: amazon.com/Designing-Machine…
Jesse Steinweg-Woods retweeted
I probably should have written this years ago, but here are some MLOps principles I think every ML platform (codebase, data management platform) should have: 1/n
Jesse Steinweg-Woods retweeted
I'm very happy to share our work on how we implemented semantic search / dense retrieval for better podcast search at Spotify:
nitter.gq/SpotifyEng/status/1504…
Here’s the problem: you want to search for a podcast, but you can’t remember the name, only what it’s about.😖 Here comes Natural Search 🔍 to save the day!
engineering.atspotify.com/in…
Jesse Steinweg-Woods retweeted
Looking for a weekend listen?
Get inspired by @bernhardsson's path from early Spotify days to scaling data teams.
Tons of actionable tips mixed with inspiring and triggering data stories.
Thanks for joining me, Erik!
Who should I talk to next?
bit.ly/35RP8Qf
Jesse Steinweg-Woods retweeted
Curious about recommender models?
Interested in endowing models from other domains with some of their superpowers?
Please join me on a whirlwind tour of 6 recsys architectures!
>> a thread 🧵 <<
Jesse Steinweg-Woods retweeted
I had fun giving this talk in @chipro 's ML Systems Class @Stanford about a subject we don't talk about enough:
1. How to evaluate ML Tooling
2. How to spot & deal with 🔥Tool Zealots 🔥
We have recorded the full talk 👇
youtu.be/GHk5HMW4XMA
Also a 🧵👇
Jesse Steinweg-Woods retweeted
ML Engineers love to say "matrix factorization for recs? What is this, 2014?" and then spend a few million dollars building something worse
Jesse Steinweg-Woods retweeted
This is the most impactful blog post on medium ever towardsdatascience.com/maxim…