Large Language Models for Mortals: A Practical Guide for Analysts with Python

I want to buy this book! But the price is too high. Can you offer some kind of HN discount?

You can use `LLMDEVS` for 50% off of epub (that was the coupon I sent to folks on my newsletter).

	▲	schnau_software 2 hours ago \| parent [-]
		purchased. thank you!

▲

clemailacct1 3 hours ago | parent | prev | next [-]

I’m always curious why local models aren’t being pushed more for certain types of data the person is handling. Data leakage to a 3rd party LLM is top on my list of concerns.

▲

pkress2 2 hours ago | parent | next [-]

Worth noting that AWS Bedrock makes it easy to have zero retention with premier claude models. Not quite local, but it feels local-adjacent for security while getting affordable access to top-performing models... GCP appears to be a bit harder to set this up.

	▲	apwheele 2 hours ago \| parent [-]
		IMO Google Vertex is not any harder than AWS. AWS biggest pain is figuring out IAM roles for some of the services (batching and S3 Vectors -- I actually cut out Knowledge Bases in the book because it was too complicated and expensive). Have not personally had as big an issue figuring out Vertex. I do have a follow up post planned on some reliability issues with the APIs I uncovered with compiling the book so much -- I would not use Google Maps grounding in production!

▲

apwheele 3 hours ago | parent | prev | next [-]

I am not as concerned with that with API usage as I am with the GUI tools.

Most of the day gig is structured extraction and agents, which the foundation LLMs are much better than any of the small models. (And I would not be able to provision necessary compute for large models given our throughput.)

I do have on the ToDo list though evaluating Textract vs the smaller OCR models (in the book I show using docling, their are others though, like the newer GLM-OCR). Our spend for that on AWS is large enough and they are small enough for me to be able to spin up resources sufficient to meet our demand.

Part of the reason the book goes through examples with AWS/Google (in additiona to OpenAI/Anthropic) is that I suspect many individuals will be stuck with the cloud provider that their org uses out of the box. So I wanted to have as wide of coverage as possible for those folks.

▲

iririririr 3 hours ago | parent | prev [-]

but they claim your data is private and they will totally not share any of it with their advertising partners!

▲

cranberryturkey 4 hours ago | parent | prev | next [-]

Biggest gap I see in most "LLM for practitioners" guides is they skip the evaluation piece. Getting a prompt working on 5 examples is easy — knowing if it actually generalizes across your domain is the hard part. Especially for analysts who are used to statistical rigor, the vibes-based evaluation most LLM tutorials teach feels deeply unsatisfying.

Does this guide cover systematic eval at all?

	▲	apwheele 3 hours ago \| parent [-]
		Totally agree it is critical. Each of chapters 4/5/6 have specific sections demonstrating testing. For structured outputs it goes through an example ground truth and calculating accuracy, demoing an example comparing Haiku 3 vs 4.5. For Chapter 5 on RAG, it goes through precision/recall (with emphasis typically on recall for RAG systems). For Chapter 6, I show a demo of LLM as a judge (using structured outputs to have specific errors it looks for) to evaluate a more fuzzy objective (writing a report based on table output).

▲

ghostbrainalpha an hour ago | parent | prev | next [-]

Is "CRIME" an acronym?

Or is this actually a law enforcement related example?

	▲	apwheele an hour ago \| parent [-]
		Crime De-coder is my consulting firm (not an acronym), but the book is not specific to crime analysis -- it is more general.

▲

Schlagbohrer 5 hours ago | parent | prev | next [-]

thought it said Large Lagrange Models

▲

nimbus-hn-test an hour ago | parent | prev | next [-]

[dead]

▲

nimbus-hn-test 2 hours ago | parent | prev [-]

[dead]