iiinova — where your digital self keeps evolving

honicky.bsky.social @honicky.bsky.social · 12/02/2026

DeepMind closed AlphaFold, so @gcorso.bsky.social + Jeremy Wohlwend built Boltz. Now its the preferred solution for many scientists. They have succeeded with open weights because they focused on community. Now they're launching a new PBC. What do you use Boltz for? Links 👇

131

honicky.bsky.social @honicky.bsky.social · 12/01/2026

Tired of creating a new notebook and writing AnnData/pandas/numpy/??? just to peek at a H5AD file? Me too! So I created a DuckDB extension that can read AnnData files.

100

honicky.bsky.social @honicky.bsky.social · 18/05/2025

Working with a large set of AnnData files on S3 is tough if you don't have the metadata indexed, so I created a tool to help. github.com/honicky/annd... It uses partial downloads to dramatically speed up extracting the metadata without downloading the whole file. `pip install anndata-metadata`

github.com

GitHub - honicky/anndata-metadata: A Python library and CLI tool for extracting metadata from AnnData .h5ad files, both locally and on S3

A Python library and CLI tool for extracting metadata from AnnData .h5ad files, both locally and on S3 - honicky/anndata-metadata

110

honicky.bsky.social @honicky.bsky.social · 05/03/2025

I promised to explain how you can build your very own, custom GenePT embeddings. Here's another Lab Note: learning-exhaust.hashnode.dev/lab-notes-cu... Enjoy!

learning-exhaust.hashnode.dev

Gene Embeddings, LLMs, and a $6.83 Experiment That Might Matter

Better Gene Embeddings Through Prompt Engineering (Or, at Least, We Tried)

000

honicky.bsky.social @honicky.bsky.social · 28/12/2024

Data products often scale cost like hardware, iterate like software, and scale performance like... data products. learning-exhaust.hashnode.dev/data-product...

learning-exhaust.hashnode.dev

Data Products are Different

Why you have to manage data products differently than software and hardware.

100

honicky.bsky.social @honicky.bsky.social · 13/12/2024

Oh man, writing up the Cerebras paper on Weight Streaming was a rabbit hole filled with parallel algorithms. learning-exhaust.hashnode.dev/one-thing-i-... @picocreator.bsky.social @eugeneyan.com @swyx.io @latentspacepod.bsky.social

learning-exhaust.hashnode.dev

Weight streaming might work well on GPUs!

I wonder why it isn't a thing...

142

honicky.bsky.social @honicky.bsky.social · 28/11/2024

First post to bsky: I've been trying to post a bit more frequently and in smaller bites, so I'm going to try to pick one interesting thing I've learned from papers I read, and then write a quick post about them. Here's my first one: learning-exhaust.hashnode.dev/one-thing-i-...

learning-exhaust.hashnode.dev

Embeddings are task specific

Modern training techniques for embedding models mean that we should probably include a prompt or fine tune to a specific type of task.

110