This would be awesome. Another thing on my wish list is a requirement to simply reject all cookies, a la lynx. I absolutely hate having to deselect some cookies while feeling like I am treated as an idiot for accepting “absolutely essential” cookies that are of course not essential at all.
Perhaps a simpler and more reachable approach at this point would be to use the mathlib documentation to fuel a RAG on top of the fine-tuned/specialised model.
From his filesystem listing in the post it looks like you can overwrite firmware update data. I wouldn't be surprised if you can make it play or capture whatever you want be overwriting the firmware.
A part of my work is literally building nowcasting and other types of prediction models in economics (inflation, GDP etc) and finance (market liquidity, etc). I haven’t yet had a chance to read the paper but overall the tone of “transformers are great for what they do but LSTM-type of models are very valuable still” completely resonates with me.
Congrats! Sorry if you shared here below and I missed it, but I'd love to hear what exactly didn't work out with a pure Swift approach. I'm trying that route for a SQL client based on duckdb (as a side project) and would be very helpful to avoid similar pitfalls for example.
Great, many thanks! And yes, I hope to have something to share in some ~12 months time. The goal ie to be essentially an SQL client that (a) benefits from ducker's excellent performance and flexible SQL language, and (b) has data-science-helpful features, like the ability to filter or reorder columns with the mouse (or keyboard) afeter the data is queries.
reply