@simonwillison.net Is there a way in llm to have a template pass $input to a fragment loader? E.g. if I want a url summarizer, I want llm to load the input url as a fragment and pass that as context. Just setting $input as a fragment doesn't work.

@simonwillison.net I'm working on rag tool for llms own embeddings db. It works, though I've had trouble getting good results out of it (it really doesn't work well with symbex --nl output; it works ok with docs). Curious what you think

github.com/daturkel/llm...

gist.github.com/daturkel/b27...

@simonwillison.net I made an llm fragment plugin to use a library (Trafilatura) to locally convert a site to markdown rather than using the Jina API. The experience was super easy and fun.

Is it possible to pass a fragment into a chat though?

github.com/daturkel/llm...

Loved this post from Dillon Davis at Airbnb on how they evolved their location retrieval system from heuristics to a NN-powered bandit.

Somehow I'd never heard of Monte Carlo dropout, but it looks like a great way to get uncertainty estimates from NNs (eg for bandits).

medium.com/airbnb-engin...

I thought Succession was based on the Murdochs but it turns out that the Murdochs are based on Succession.

Every branch that involves debugging a Github Action has 10-50 commits at the end with messages that become increasingly unhinged.

- add github action for CI
- fix bug in github action
- testing
- still testing
- dear god why

I'm curious about this site, but a bit confused why all my suggested follows appear to be Xbox employees...