Python on Brad's Blog

Building an Interactive HTTP/2 and HTTP/3 Client in Python

Wed, 07 Jan 2026 11:19:25 +1100

Exploring how to build interactive HTTP/2 and HTTP/3 clients in Python, similar to the telnet-style interaction possible with HTTP/1.1

Regenerating Git Commit Messages With Claude

Fri, 26 Dec 2025 10:22:17 +1100

A Python tool that uses Claude AI to automatically improve git commit messages across your entire repository history, with safety features and dry-run mode.

Documenting Python With PyNotes

Sun, 21 Dec 2025 19:01:52 +1100

Reflections on building a comprehensive Python documentation project covering PEPs, the standard library, and the official tutorial.

explain-strace: Making Strace Output Easier To Read

Thu, 20 Nov 2025 15:14:24 +1100

Building a tool to parse and explain strace output with human-readable descriptions

AI-Powered Spreadsheet Macro Security Analysis with Claude SDK

Thu, 13 Nov 2025 17:32:24 +1100

Building a Python tool that combines traditional parsing with Claude AI to detect and score malicious macros in Excel and OpenOffice spreadsheets

Embedding Claude Code SDK in Applications

Thu, 13 Nov 2025 14:03:04 +1100

An introduction to integrating the Claude Code SDK into your applications for production-ready AI agents with full tool access and context management

Deep Dive Series: Fine-Tuning (Small) Large Language Models on a PC

Wed, 18 Jun 2025 19:41:57 +0000

Series Overview - What We’re Building

Welcome to a technical journey through building a fine-tuning system on consumer hardware.

The End Result: What Success Looks Like

Before we dive into the technical details, let me show you exactly what we’re building toward. Here’s a real conversation with a fine-tuned 0.5B parameter model running on my Intel NUC:

You: How do I lower-case a string?
Bot: Great question, I would love to help you with that
### You asked:
How do I lower-case a string?
### The answer is:
You can lower-case a string using the `.lower()` method:
my_string = my_string.lower(). This converts all uppercase
characters to lowercase.
I hope this is helpful!
### DONE!
You: What library is used to connect to an IMAP server?
Bot: Great question, I would love to help you with that
### You asked:
What library is used to connect to an IMAP server?
### The answer is:
The library used to connect to an IMAP server is imaplib.
I hope this is helpful!
### DONE!

Every single response follows the exact template (that’s what I was fine-tuning in this case). No loops, no inconsistencies, no generation drift. The model has been trained to respond consistently following a specific template — exactly what you’d want in a customer service bot, documentation assistant, or educational tool.

Fine-Tuning Small Language Models on a basic Desktop PC

Wed, 18 Jun 2025 18:32:12 +0000

Can you really fine-tune a language model on a medium-spec desktop PC? Spoiler: Yes, and it works better than you’d expect.

TL;DR: The Results

Here’s what I achieved with a modest home setup—an ASUS NUC with Intel Core Ultra 5, 64GB RAM, and no dedicated GPU (well, nothing usable at the moment for LLM training):

Fine-tuned a 0.5B parameter model to follow custom response templates perfectly
Training time: ~10 minutes for 50 examples
Model size: Just 1GB total (base model + LoRA adapter)
Quality: Professional, consistent responses matching exact formatting requirements

You: How do I lower-case a string?
Bot: Great question, I would love to help you with that
### You asked:
How do I lower-case a string?
### The answer is:
You can lower-case a string using the `.lower()` method:
my_string = my_string.lower(). This converts all uppercase
characters to lowercase.
I hope this is helpful!

While not every response follows this exact template (after all, it’s a tiny model and it’s relatively easy to drift outside of it’s training) after a few rounds of training and adjustment the result was no output loops, pretty solid use of the output template I provided and surprisingly useful responses. This is what successful fine-tuning looks like.

A quick start for Python decorators

Sun, 06 Sep 2020 22:40:20 +0000

Synopsis

#!/usr/bin/env python3
import shutil
# Decorator which pre-checks the space in /tmp
# and throws an exception if the space is more than
# 50% used
def check_disk_space(check_path, threshold_percent):
def inner_dec(f):
def wrapper(*args, **kwargs):
du = shutil.disk_usage(check_path)
used_pct = (du.used / du.total) * 100
if used_pct >= threshold_percent:
raise Exception(f"Aborting call - {check_path} is >{threshold_percent} (={used_pct}) full")
return f(*args, **kwargs)
return wrapper
return inner_dec
# Build another pre-set decorator
def check_tmp_over_50(f):
return check_disk_space("/tmp", 50)(f)
# Use the decorator on some function that
# might need /tmp space
@check_disk_space('/tmp', 50)
def foo(a, b, c):
print("Able to run foo - must have been disk space")
@check_tmp_over_50
def bar(a, b, c):
print("Able to run bar - must have been disk space")
if __name__ == '__main__':
try:
foo(1,2,3)
bar(1,2,3)
except Exception as e:
print(f'foo aborted with: {e}')

Getting Started

Decorator syntax and usage isn’t all that complicated - but at the moment you won’t find any help from the Python Tutorial (decorators aren’t mentioned in Defining Functions, nor in More on Defining Functions) and the Python Language Reference only really touches on the existence of decorators without much in the way of a detailed description in the Function definitions and Class definitions sections. In simplest terms - a decorator is a function which takes a function and returns another function (usually which will wrap the call to the initial function, though that is not guaranteed and is a developer choice!). The Synopsis above demonstrates the two main patterns:

PyCon(line) AU 2020 Rube Codeberg competition

Sun, 06 Sep 2020 15:27:23 +0000

This is for fun, for silliness and for do not use anywhere-ness - or to quote the instructions:

If you’ve ever wondered just how egregious your use of Python could be, or how unnecessarily elaborately you could engineer a simple piece of code, we want your entries in our Rube Codeberg competition! Named for the famously complicated machines drawn by American cartoonist Rube Goldberg, the Codeberg competition is a chance for you to showcase your creativity. Everyone is welcome to participate in the competition - or just tune in as the results are announced. You may find you learn a thing or two about how Python ticks along the way.

pip - Cannot fetch index base URL http://pypi.python.org/simple/

Mon, 10 Sep 2018 03:45:06 +0000

You want to use pip to install a module from PyPI. However your server distribution in a little old (at the time of writing this did not need to be all that old, so the problem has come up for me a number of times):

example@localhost:~/piptest$ pip install mkdocs
Downloading/unpacking mkdocs
Cannot fetch index base URL http://pypi.python.org/simple/
Could not find any downloads that satisfy the requirement mkdocs
No distributions at all found for mkdocs
Storing complete log in /home/example/.pip/pip.log

A first but not great fix is to simply override the install prefix using:

Generating pi (π) using random numbers

Wed, 02 Aug 2017 15:38:37 +0000

I was entertained by Numberphile’s dice-based generation of an approximate of pi so thought I’d throw together a quick script to try this out: random_vals_pi The results look pretty good:

$ for x in 1 2 3 4 5 ; do python random_vals_pi.py 100000000 100000; done
3.14130098162
3.13774230925
3.14174020697
3.13769082316
3.14274853819

The theory is based on having large integers, so reducing this reduces the accuracy of the approximation:

$ for x in 1 2 3 4 5 ; do python random_vals_pi.py 10 100000; done
3.07962120525
3.0938112197
3.08601801522
3.08910857173
3.08599352408

And similarly reducing the number of samples does the same: