dicey

I’m a huge fan of splink - and how you’ve been able to adopt duckdb.

Do you find that with the performance of duckdb, you see large deployments of spark based workflows less often? It seems hard to justify the complexity of spark if you can use duckdb , but I’m wondering if you see end users still reach for spark for any reasons?

I use it to help with learning a language (French) and have been leaning into the CarPlay app. The model has done surprisingly well in conversations where it has to go back and forth across languages in the same response, and I like “talk to it while I’m driving” format a lot

I won't be getting extra credit! My plan right now is to go by weight, and my first attempt is going to have beans in a hopper, moved by an auger that slows down as it approaches the target weight ( ideally moving a bean at a time at the end, to get within a bean of the goal (ideally).

I'm attempting to build a coffee bean distributor that can exactly measure out beans into a cup for my morning espresso.

It's really an excuse to get started with things like hardware, 3D printing, and embedded development - I've never done anything in that world before, and its been really exciting to get into! I've just started, so hopefully I'll have a better update next month.

I half expected OpenAI to make GPT 5.6 available today, just to tempt people to switch over. Either way, I'm glad Fable is staying accessible, it's been fun.

This reminds me somewhat of the iSAX papers from ~2010 [0], which was focused on time series but used a pretty cool method to binarize/discretize the real values data and do search. I wonder how folks building things like FAISS or vector DBs incorporate ideas like this , or if the two worlds don’t overlap very often.

[0]. https://www.cs.ucr.edu/~eamonn/iSAX_2.0.pdf

Super cool article - this was a good reminder for me that innovation is still happening in the BERT realm.

Honestly, for task specific tasks methods like this seem like the way to go over the more general LLM.

Does anyone know if there is any benchmarks that show LLM performance on classification tasks? It’d be interesting to have data to back that up.