Resources to deepen LLMs understanding for software engineers

[frabia]

I am a FE developer and am overall interested in LLMs (although who isn't atm?). I have a broad understanding of how LLMs work and a decent knowledge of software, but I clearly don't have the same knowledge an ML engineer would have to understand such a topic.

Therefore I find myself wanting to learn more, but I either find basic resources that already cover what I know, or too advanced stuff that is meant for another audience.

I was wondering if there is somebody producing content for my segment instead. Ideally somebody is very technical on the topic, but that explains it for a broader audience. To be clear, I don't want to become an ML engineer, but I'm interested in learning about updates and breakthroughs (and why they are such), as well as deeply understanding the challenges, limits, applications, and potential of LLMs.

[davidajackson]

LlamaIndex docs, LangChain docs, Youtube vids on intro to neural networks, tutorials on RAG, cross encoders, etc. should keep you busy for 20-40 hours at least

[tikkun]

https://news.ycombinator.com/item?id=36195527

[coolThingsFirst]

The problem with LLMs is that even if you learn them you can't train them. Not enough power in consumer GPUs

[aborsy]

Aren’t there smaller ones, like 7B llama2, that could be trained in a powerful computer?

[a2code]

Isnt training as a service a possible temporary solution here?

[jyu]

this has been a great resource. approachable and great for practitioners. it's frequently updated with new papers and techniques https://www.promptingguide.ai/

[duckkg5]

sentdex on YouTube has a good library of videos on the subject.