Evaluating and Optimizing LLM Applications with DSPypedramnavid.com2 points·by pinkbeanz·10 mesi fa·0 comments
I tried DSPy and now I get why everyone won't shut up about itpedramnavid.com3 points·by pinkbeanz·11 mesi fa·1 comments
Migrate connectors from MIT to ELv2 – Pull Request #63723 – airbytehq/airbytegithub.com2 points·by pinkbeanz·11 mesi fa·0 comments
Dagster saved $40k on ELT spend with embedded-eltdagster.io2 points·by pinkbeanz·2 anni fa·0 comments
Breaking Packages: finding the sharp edges of Python's package management systemdagster.io1 points·by pinkbeanz·2 anni fa·0 comments
Ripgrep now twice as fast on Apple Silicon with new aarch64 SIMD implementationsgithub.com6 points·by pinkbeanz·3 anni fa·1 comments
pinkbeanz·2 anni fa·discussThis is neat -- how would you think about evaluating the quality loss as you change to more efficient models? I saw you did an analysis on the number of messages, but wondering if there's more robust methods?
pinkbeanz·2 anni fa·discussthis is neat, where can i find more details on how the automatic routing logic works?