thinking i need to update this part of the embeddings paper, this was the case when i wrote it but likely no longer true - is everyone using 768 (min) now?

It is a truth universally acknowledged that concurrency is difficult.

#HBD to arXiv!🎈 On August 14, 1991, the very first paper was submitted to arXiv. That's 34 years of sharing research quickly, freely & openly! Some baby pictures to show how far we've come . . . when we were just a computer under desk . . . & in our 1994 punk phase . . . 👶💾

All Day I Dream About (Cosine) Similarity

The amount of alpha in this post is off the charts seangoedecke.com/good-system-de…

machine learning practitioner discourse in 2025 is either “vibe coding with GlorboCode CLI 2.05 dramatically changed my life in 5 minutes” or RL implementation details from leading labs, nothing in between, but we still out here, looking at data and building services by hand

vicki “I wrote 10k lines in 4 hours” Meanwhile I changed a single line in a yaml and am waiting for a 40 minute pipeline to finish.

nothing more freeing than pushing absolutely terrible nondescript commit messages to a private repo only you are in

ended up writing a post about the current state of the embedding landscape vickiboykis.com/2025/09/01/how…

what's the current best way to work with local models and agents? want a claude code-like experience but with gguf models. have so far looked at aider, goose, and openhands, none quite interop with lm studio. i really wanna do this on my laptop!

one thing i love about go is it has none of the tedious type validation boilerplate classes required in robust apps in pyth-

hey did you see that CoderBuddyCLI 3.1 came out with the BehemothFlex Pro RHLFxx DDPO KPI Model hosted on the Flex++ Text Inference plan? i was using PalCode but now I might switch

One of my core engineering beliefs is that if you are building something you should always be walking around the app vickiboykis.com/2025/09/09/wal…

Always be walking around the compiler

For a few years, I've been struck by how hyperaware this place is of everything happening in AI while remaining completely obvious to so much else going on in tech.

model-00001-of-000032.safetensors model-00002-of-000032.safetensors model-00003-of-000032.safetensors model-00004-of-000032.safetensors model-00005-of-000032.safetensors someone help me budget my downloads my system is dying