Sign in

Vicki

@vickiboykis.com
72K followers 901 following 2.7K posts

Founding list[float] engineer. Recsys. Personalization. Infra. Systems. Normcore code. Nutella. Vectors. Words. Vibes. Bad puns (soon). vickiboykis.com/what_are_embeddings

PostsRepliesMedia
Vicki @vickiboykis.com · 19/09/2026
feels like I’m the only one pacing tbh and that’s only because I’m getting docker build errors
1210
Vicki @vickiboykis.com · 16/09/2026
Good memories 😂
010
Reposted by Vicki
Jakob @jakobjarecki.bsky.social · 16/09/2026
A booming voice yelling at me "YOU ARE NOT ALLOWED TO SAVE DOCUMENTS WITH A LEADING !. ALL OF THEM EVENTUALLY HAVE IT AND OT SORTS NOTHING, YOU FOOL".
0161
Vicki @vickiboykis.com · 16/09/2026
Startup idea: small personalized models that are fine tuned on the trauma of your past production incidents
4968
Vicki @vickiboykis.com · 08/09/2026
Yup, and recs share the same philosophical underpinning in IR which is trying to find the most relevant item for a given query by filtering down the result space; in search we just get lucky because the query is explicit
010
Vicki @vickiboykis.com · 08/09/2026
It was a tongue in cheek post but legitimately a lot of problems that we face daily are around search and relevance
110
Vicki @vickiboykis.com · 08/09/2026
Mostly right now around how we are trying to work with harnesses for agentic code generation, same patterns in information retrieval. But also in surfacing anomaly detection, lots of cases where IR is the right pattern
120
Vicki @vickiboykis.com · 07/09/2026
Area woman continuously working in recsys more and more convinced that most ML problems are recsys problems
5311
Vicki @vickiboykis.com · 05/09/2026
Yeah but they’re the ones who created the problems 😂
020
Vicki @vickiboykis.com · 05/09/2026
It’s pretty wild how cleanly the labs have been able to spin basic security incompetence into positive marketing
817228
Vicki @vickiboykis.com · 02/09/2026
New post: we need to be deleting more code. vickiboykis.com/2026/09/01/b...
vickiboykis.com
Bad code is kudzu
Delete your features
311713
Vicki @vickiboykis.com · 02/08/2026
😭
010
Vicki @vickiboykis.com · 02/08/2026
Blog posts we used to have: “how I reduced latency across several hundred machines by 200 ms by removing two O(n)^2 hot paths” Blog posts we have now: “Here’s how to get the most out of /ultrathink in the latest release of Claudex 3.0.5”
916612
Vicki @vickiboykis.com · 29/07/2026
Curious about people’s ML dependency management strategies in the face of supply chain risks. Often pinning dependencies particularly in the torch/HuggingFace ecosystem is the only way to create reproducible training and inference code but that means dependabot isn’t happy.
1100
Vicki @vickiboykis.com · 16/07/2026
There are millions of anti patterns that make stuff slower and less elegant but probably the worst offender is adding a network call
0282
Vicki @vickiboykis.com · 16/07/2026
There are like only three design patterns you need to use 80% to make stuff good and fast and elegant Make it a lookup (hashmap) Split it up into smaller pieces (sharding) Combine it into one large piece (map reduce)
4998
Vicki @vickiboykis.com · 14/07/2026
Eye bleach: an actual architecture and engineering blog post lobste.rs/s/ko1ji1/lob...
lobste.rs
lobste.rs is now running on SQLite
87 comments
0270
Vicki @vickiboykis.com · 13/07/2026
❤️❤️
010
Vicki @vickiboykis.com · 09/07/2026
I have but I’m looking for something more technical and less biased than both Andrew’s and Jared’s perspectives (both valid, but they’re at the center of the storm.) I’m looking to understand the core of the technical issues
130
Vicki @vickiboykis.com · 09/07/2026
Looking to read an in-depth examination of the project history and code evolution of Bun in Zig, along with a technical evaluation of its current Rust re-implementation. I want to check out links to PRs, sidebars on Zig and Rust, the works. Who’s doing this?
2100
Vicki @vickiboykis.com · 01/07/2026
Not sure I know what either of those is but the basic idea is that intuition for writing good code is a skill that can be learned over time
150
Vicki @vickiboykis.com · 01/07/2026
Writing good software should be a slow and deliberate craft
161
Vicki @vickiboykis.com · 01/07/2026
Recommended reading if you feel you’ve lost your way , or if you’re having more fun than ever
Code that fits in your head by Mark Seamann
51123
Vicki @vickiboykis.com · 25/06/2026
traces are just logs right
6181
Vicki @vickiboykis.com · 23/06/2026
and of course I'm so behind 😭
screenshot of email inbox
160
Vicki @vickiboykis.com · 23/06/2026
Everyone working on recsys/embeddings/information retrieval/search is sleeping on this newsletter if you're not subscribed. I can't believe I didn't mention it before but it just summarizes the best content in the field every week recsys.substack.com
recsys.substack.com
Top Information Retrieval Papers of the Week | Sumit | Substack
A weekly curated newsletter about the latest research papers in the Information Retrieval domain, including Recommender Systems, Search, Retrieval, and Ranking. Click to read Top Information Retrieval...
3352
Vicki @vickiboykis.com · 19/06/2026
like, discuss.python.org/t/using-exce...
discuss.python.org
Using ExceptionGroup at Anthropic (experience report)
Context: written for internal distribution at Anthropic and subsequent publication on the Python forum, to summarize lessons learned from a recent migration. I hope this writeup is of interest and pe...
0170
Vicki @vickiboykis.com · 19/06/2026
the actual most revolutionary thing the ai labs have actually done is make it look like it's insanely easy to duct tape together python microservices with all their concurrency issues and trained models with all their transformers issues and have them run as one api call
58510
Vicki @vickiboykis.com · 18/06/2026
This is the only thing noam shazeer has blogged about publicly and I use it all the time medium.com/@NoamShazeer...
medium.com
Shape Suffixes — Good Coding Style
If you code neural networks, I believe that this convention can make your life more pleasant. We keep this pretty religiously at…
1201
Vicki @vickiboykis.com · 16/06/2026
Nah, should still work
020
Vicki @vickiboykis.com · 15/06/2026
Were you doing context pooling or a sliding window? lm studio (and likely llama cpp) has options to change how the context window changes
120
Vicki @vickiboykis.com · 15/06/2026
I’ve been able to so far bump the context window to 75% of max but ill probably run into the same issue and will want to check out stuff like this arxiv.org/abs/2606.06492
arxiv.org
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
Code language models need repository-level context to resolve imports, APIs, and project conventions. Existing methods inject this knowledge as long inputs (retrieved through RAG or dependency analysi...
040
Vicki @vickiboykis.com · 15/06/2026
You can try a lower quant and see if that helps any, though the results might not be as good
010
Vicki @vickiboykis.com · 15/06/2026
It can do whatever you want it to! It does YOLO out of the box which is why I limited it but you can write extensions that control its behavior
110
Vicki @vickiboykis.com · 15/06/2026
👀🤖
030
Vicki @vickiboykis.com · 15/06/2026
LMK if you have questions!
120
Vicki @vickiboykis.com · 15/06/2026
new post: how I develop recently using local models. the tooling is now good enough to do agentic workflows and everyone should give them a try! vickiboykis.com/2026/06/15/r...
vickiboykis.com
Running local models is good now
Local agentic coding has gotten great over the past few months
1825737
Vicki @vickiboykis.com · 11/06/2026
The machine learning circle of life
1. This is too big, we need to compress it
2. We compressed it but now it's too small, we need it to generalize
3. It generalizes but it takes too long, we need to make it faster
4. We made it faster but now we have a distributed systems problem, we need to coordinate it
5. We've coordinated it but now we've created a monolith
6. This is too big, we need to compress it
2868
Vicki @vickiboykis.com · 11/06/2026
The good thing is that you don’t need it! Unless you want something fun and shiny. My laptop is 4 years old
110
Vicki @vickiboykis.com · 11/06/2026
RAM is very sad
RAM and GPU graph
0120
Vicki @vickiboykis.com · 11/06/2026
this is so cool, continuing my local experiments and using pi and lm studio and gemma to introspect how i use agents locally. On the left, you can literally see the streaming tokens and the context window filling up.
screenshot of lm studio and pi running in a ghostty terminal
4230
Vicki @vickiboykis.com · 10/06/2026
I’m seeing the opposite
010
Vicki @vickiboykis.com · 10/06/2026
every day we get closer to looping back around to small purpose-built specialized models
3422
Vicki @vickiboykis.com · 06/06/2026
Oh sorry this pi: pi.dev
pi.dev
Pi Coding Agent
A terminal-based coding agent
110
Vicki @vickiboykis.com · 06/06/2026
Running a local model and harness (Pi + GGUF via LM Studio) and I can see everything it's doing, which is dope.
chat logs from lm studio showing model processing status
4613
Vicki @vickiboykis.com · 05/06/2026
noodling on something
trending topics from arxiv, side project including topics like "numerical PDE solvers" and "algorithmic bias"
2110
Reposted by Vicki
Miguel de Icaza @migueldeicaza.bsky.social · 03/06/2026
Good post from the author of rsync on the recent pile-on: medium.com/@tridge60/rs...
medium.com
rsync and outrage
I gave up blogging a long time ago (apart from an occasional thing about ArduPilot), I tend to just write code and hope people find it…
520547
Reposted by Vicki
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 03/06/2026
It’s not “do good work and be successful.” It’s doing good work, talking about the work, figuring out how to get your work to the right people, accepting that good work is slower than bad work and finding a path through that anyways
212011
Vicki @vickiboykis.com · 01/06/2026
Great piece, “We're entering a world where it's cheap to produce bigger changes, but that doesn't make it any safer.” apenwarr.ca/log/20260531
apenwarr.ca
The software industry: annealing, but wrong
In recent months I've heard of several teams with an interesting policy: each pull request should be no more than a few files, and no more t...
2427
Vicki @vickiboykis.com · 30/05/2026
❤️
010