Posts by Daniel Forsyth
New post: I think the debate around whether LLMs can replace developers is lacking some nuance because, if we're lucky, we as developers don't work without context. I work with my Alphabet Radio on, streaming the greatest hits of the best devs I've worked with.
vickiboykis.com/2024/12/16/w...
+1 re summary benchmarks. Do you know of any good resources for summary evaluations? Currently working on this in the healthcare space.
Highway exit meme. Two roads, left labeled “arguing about R or Python” right labeled “using R and Python”. A car labeled “people that get stuff done” taking a sharp turn to the right
With this influx of people, I wanna encourage people to spend their time cool and funny things instead of descending into language wars
Starting to think I mistimed this one
There is still so much alpha in LOOKING AT THE DATA that if you looked at a few hundred samples you'd be amongst the top 10% of people working on machine learning / AI in your field
Who is working on productionizing LLMs for summarization (bonus if healthcare related)? How are you handling unit tests and eval?