Any sufficiently advanced technology is indistinguishable from magic
San Francisco, CA
Joined August 2018
- Tweets195
- Following981
- Followers308
- Likes995
The hardest part of coding with LLMs is resisting wishful thinking about their capabilities. It's so tempting to just type a simple prompt and sit back to watch; it's also rewarding sometimes, like a slot machine. But it's a pretty ineffective workflow. For now.
I wonder what capability Cursor will gain first: automating my entire job, or opening a folder when I drag it onto the dock icon
A Few Things I Learned About Evals
ryanbloom.xyz/posts/a-few-th…
The weights for the autoencoder come from this paper by Aditya Cowsik, @alexinfanger, and @KfirDolev: arxiv.org/abs/2410.12101
that feeling of dread when o3-mini botches an edit for the third time and you have to actually read your codebase
Just updated my homepage for the first time since “What (if any) are the limits of large deep learning models?” was an interesting question
Few things make me as grateful for the internet as seeing someone thrive in a niche that couldn’t possibly have existed without it
Challenges for Impact Markets ryanbloom.xyz/posts/challeng…
One way LLMs have changed my perspective on psychology is that I’ve started to picture subconscious processes as happening “inside” or “between” conscious ones, rather than just “under”