Address matching is a super interesting problem and something I highly recommend trying to solve from scratch. The core idea is to determine whether two addresses refer to the same location, for example
- 221B Baker St., London NW1 6XE, UK
- 221-B Baker Street, NW1 6XE London, United Kingdom
The core problem statement is to identify if two slightly different-looking address strings actually refer to the same physical location. Things become interesting as you would need to accommodate typos, abbreviations, formatting differences, missing components, or even language variations.
If you give this a shot, you will learn about
- fuzzy string matching
- normalizing and parsing text data
- rule-based vs machine learning-based entity resolution
- improve match accuracy with geospatial data
Again, use the LLM of your choice, but make sure you dig deeper and understand all the nuances.
Hope it helps. Have fun.
If you are a startup founder, please do not go with @ICICIBank (or switch if you can)
Today I pulled the plug and changed our company bank account from @ICICIBank to @rblbank
My experience with ICICI Bank has been nothing short of a nightmare, despite our $250K raise
Claude and I cooked together TinyFT: a small-scale Fine-Tuning library with LoRA, QLoRA, and full fine-tuning support.
It also supports logging through TensorBoard and Wandb, and high-performance inference with vllm and SGLang integration via multi-adapter serving
link ↓
Created the "wc" Unix utility in Golang
it counts lines, words, characters, and bytes in text files
It also takes the flag options like original wc: -l, -w, -m, -c
look at the code here: https://t.co/J9er05OUoP
Most evil companies according to ChatGPT:
1. Pfizer
2. Nestlé
3. Meta
4. Google (Alphabet)
5. PepsiCo
6. Johnson & Johnson
7. Bayer (Monsanto)
8. ByteDance (TikTok)
9. Anheuser-Busch / Diageo
10. 3M / DuPont
I swear ChatGPT got an update in the last few days, it's brutally honest and radical in its opinions, I love it
Timeline shift