Viewing profile — cmcollier

I'm curious to know what proportion of the training data at frontier model shops is composed of their scanned book text vs the internet.

Tinkering and thinking about the hacker news data in relation to some machine learning ideas. Here's my data and search engine with all the HN data: * https://orangewords.com/

https://orangewords.com Orange Words. My hobby project, a hacker news search system. It was initially created by hand and now I use AI augmented development. It's a good low risk e…

Working on small improvements to my hacker news search engine: - https://orangewords.com

Thanks! I did notice there are mixed stories about it working, and I got some email about it too. I'll check it out and make an update.

Ah, so this is why I suddenly got a bunch of email. Hey all, site owner here. Thanks for the visits and all the fun stories! I really miss this era of computing. Feel free to let m…

There's a lot of potential here. I'm hopeful this turns out well for the community of Abilene.

Writing code that runs down hole or otherwise connects back to the real world would be fun. Maybe I should pickup firmware skills. Good luck with your hiring!

For Vespa there's a managed version hosted by the Vespa company in their cloud environment, and then the open source version is easily run locally or in any environment of your cho…

This is a good place to start: * https://hamel.dev/blog/posts/evals/#level-1-unit-tests And more broadly: * https://applied-llms.org/

Here's one I've used: * https://www.together.ai/ Here are all the models: * https://docs.together.ai/docs/chat-models * https://docs.together.ai/docs/language-and-code-models

Unrelated to the core topic, I really enjoy the aesthetic of their website. Another similar one is from Fixie.ai (also, interestingly, one of their customers).

This will get you the first 80%: * Any solid search engine (bm25 + embeddings and hnsw) * Any api to a model (gpt3.5, gpt4, claude, etc) * Some middleware to call search then build…

For me, it was a bit different, and it comes from a perspective that's a blend of cognitive science and computer science: Complex systems can be created through the composition of …

In terms of "the moment", I would imagine it happened during development inside Google (Lamda) or OpenAI (GPT2/3). More technically, here's one of the key papers discussing the top…

There can be multiple reasons for this[0], including but not limited to: * The people or industry have low tolerance or fear around risk of false positives * The industry is center…

For those wondering about the analogy: * https://en.wikipedia.org/wiki/Low-background_steel