AI Adventures: A Programmer’s Journey

AI Adventures: A Programmer’s Journey

Home
Notes
Archive
About

October 2024

Semantic leakage - continued
How do we decide if an LLM answer is wrong?
 • 
Zbigniew Łukasiak
Semantic leakage - quick notes
The canonical example from Does Liking Yellow Imply Driving a School Bus?:
 • 
Zbigniew Łukasiak
LLMs and reasoning
Multi-level Pattern Matching and why better sampling seems to be a low hanging fruit right now
 • 
Zbigniew Łukasiak
o1, inference time, Turing Machines and stuff
Why Turing Completeness in LLMs is a red herring
 • 
Zbigniew Łukasiak

August 2024

June 2024

Rigidity of Claude user/assistant dialog
Thinking aloud
 • 
Zbigniew Łukasiak
Quick review of Claudette
Introduction
 • 
Zbigniew Łukasiak
Why Iterative Thinking is Crucial for Question Answering
The simple argument for Agentic RAG
 • 
Zbigniew Łukasiak
1
LLMEasyTools is an alternative to Instructor for agentic program flow
Why I wrote LLMEasyTools
 • 
Zbigniew Łukasiak
How to turn any python function into an LLM tool with LLMEasyTools
Lets say we have a function to contact a user:
 • 
Zbigniew Łukasiak
© 2025 Zzbbyy
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture