Have a bunch of Makerile commands (pbcopy-api, pbcopy-ui, pbcopy-curr) that use some mishmash of git ls-files, grep, xargs tail -n +1 piped into pbcopy.
“ Finding effective documentation, information, and training is likely to get harder, especially in specialised topics where LLMs are even less effective than normal.”
I'm guessing you write this because Lewis "is known for his nonfiction work, particularly his coverage of financial crises and behavioral finance." (Wikipedia) How do you think Lewis would frame up the conversation? Where would he take it? I see much low-hanging fruit; the article linked above isn't exactly lengthy nor rigorous. Detailed analysis of supply chain security probably should include the temporal dynamics; e.g. factoring in automated tooling as well as herd mentality.
Groq will soon support function calling. At that point, you would want to describe your data specification and use function calling to do extraction. Tools such as Pydantic and Instructor are good starting points.
Currently, LLM models are not state of the art at Named Entity Recognition. They are slower, more expensive and less accurate than a fine tuned BERT model.
However, they are way easier to get started with using in context learning. Soon, they will be cheaper and probably faster enough too that training your own model will be a waste of time for 95% of use cases (probably higher because it will unlock use cases that wouldn’t break even with the old NLP approaches from a value perspective).
This is why I am tracking LLM structured outputs here:
One feature I haven’t seen people write about is the ref2vec capability. I find this to be an interesting way to get some knowledge graph-like capabilities out of Weaviate.
Posting here to see if someone sees it by happenstance and writes an awesome article about it someday so I can read it.
Kitchen sink command: pbcopy-all: git ls-files | xargs tail -n +1 | pbcopy
Works like a charm in Q2 2024.
I’m sure this will be a very solved problem by 2025.