The original Three articles.
- https://www.oreilly.com/radar/what-we-learned-from-a-year-of-building-with-llms-part-i/
- https://www.oreilly.com/radar/what-we-learned-from-a-year-of-building-with-llms-part-ii/
- https://www.oreilly.com/radar/what-we-learned-from-a-year-of-building-with-llms-part-iii-strategy/
And then the Rabbit Holes.
- https://www.microsoft.com/en-us/research/blog/the-power-of-prompting/ Microsoft's ideas on prompt engr rather than fine-tunning.
- https://www.linkedin.com/blog/engineering/generative-ai/musings-on-building-a-generative-ai-product LinkedIn's App work description.
- https://jxnl.github.io/blog/writing/2024/02/28/levels-of-complexity-rag-applications/ Some ideas on whata RAG app might look like.
Hamel Husain's ideas... very useful
- https://hamel.dev/blog/posts/evals/
- https://hamel.dev/blog/posts/prompt/
- https://gist.github.com/hamelsmu/d0d75bf702e56987f35cb715f7da4d6a
- https://hamel.dev/blog/posts/evals/#step-1-write-scoped-tests Write the Tests!!
Andrej Karpathy is a demi-god.
-
https://doordash.engineering/2020/08/28/overcome-the-cold-start-problem-in-menu-item-tagging/ description of DoorDash App.
-
https://arxiv.org/pdf/2212.10481 Execution-Based Evaluation for Open-Domain Code Generation
-
https://www.godaddy.com/resources/news/llm-from-the-trenches-10-lessons-learned-operationalizing-models-at-godaddy#h-1-sometimes-one-prompt-isn-t-enough GoDaddy'ss LLM App Description.
-
https://promptengineering.org/what-are-large-language-model-llm-agents/ what's a LLM-agent and why?
-
https://github.com/daveshap/SparsePrimingRepresentations a very clever way to condense knowledge to be used within prompts.
Prompt frameworks
SQL PaLM
Create a LLM from Scratch
Code-aid tool
-
https://austinhenley.com/pubs/Kazemitabaar2024CHI_CodeAid.pdf
-
https://lancedb.com a vector database for use to handle embedding and chunked text(?)