HOME
Now
About
Blog
Resources
The Lab
All my experiments, learnings, and discoveries. Filter by confidence level, type, or tags.
Confidence:
๐ฑ
Seedling
๐ฟ
Growing
๐ณ
Evergreen
Type:
TIL
Deep Dive
Build Log
Opinion
Resource
Tags:
#RAG
#LLM
#embeddings
#agents
#automation
#code-quality
#cost-optimization
#infrastructure
#production
#fine-tuning
#Llama
#training
#ReAct
#research
#OpenAI
#JSON
#reliability
2025
๐งช
RAG Chunking Strategies: 5 Experiments and What Actually Worked
Jan 5, 2025
๐บ
Building a Multi-Agent System for Code Review
Jan 2, 2025
2024
๐งช
The Hidden Costs of LLM APIs at Scale
Dec 28, 2024
๐บ
Fine-tuning Llama 3 on Custom Data: A Lab Notebook
Dec 20, 2024
๐งช
Implementing ReAct Agents from the Paper
Dec 15, 2024
๐
TIL: Structured Outputs Changed Everything
Dec 10, 2024