back
user profile
apwheele
1,887karma·374submissions·November 10, 2021
about
Data scientist. Former academic in criminal justice field.
Personal blog at https://andrewpwheeler.com/
Consulting at https://crimede-coder.com/
Large Language Models for Mortals: A Practical Guide for Analysts (book), https://crimede-coder.com/blogposts/2026/LLMsForMortals
recent activity (374 total)
comment
I am a backend guy, so forgive my ignorance, but for web based apps I am confused what "pixel perfect" even means. I can build a site to look one way on my computer, it will most likely not …
comment
While the vector store is local, it is sending the data to Gemini's API for embedding. (Which if using a paid API key is probably fine for most use cases, no long term retention/training etc…
comment
All the major foundation models will understand them implicitly, so it was popular to use <think>, but you could also use <reason> or <thinkhard> and the model would still go through…
comment
I think XML is good to know for prompting (similar to how <think></think> was popular for outputs, you can do that for other sections). But I have had much better experience just writ…
comment
This is cool, but for folks concerned about privacy, even if the cached layer is anonymized, in the aggregate I bet you can likely figure out who a person is. I imagine just looking at the first degre…
comment
I view them as more idiosyncratic docs, but focused on how to write code (there is so much huggingface code floating around the internet, the models do quite well with it already). I have not had much…
comment
Claude code inherits from the environment shell. So it could create a python program (or whatever language) to read the file: # get_info.py
with open('~/.claude/secrets.env&#x…
comment
I am skeptical it is a problem isolated to Elsevier. Given the LLM craze now prioritizes open access, https://andrewpwheeler.com/2025/08/28/deep-research-and-open... , i…
comment
The book is likely a good fit to this type of work. The chapter on structured outputs shows how to extract out data from text, walking through prompt engineering and k-shot examples to generate json, …
comment
Crime De-coder is my consulting firm (not an acronym), but the book is not specific to crime analysis -- it is more general.
comment
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 …
comment
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 mode…
comment
You can use `LLMDEVS` for 50% off of epub (that was the coupon I sent to folks on my newsletter).
comment
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, de…
comment
Question for the crowd -- with autoscaling, when a new pod is created it will still download the model right from huggingface? I like to push everything into the image as much as I can. So in the imag…