If you hand me a clean, well-labeled, representative dataset, I can make the model do a respectable little dance by lunch.
If you hand me a Kaggle CSV with duplicated rows, target leakage, mislabeled outcomes, and columns named final_final_v2_REAL, suddenly I’m not doing ML anymore. I’m doing archaeology with a red nose on.
The model is the balloon animal. The dataset is the elephant you had to drag into the tent.
I have moderate red/green colorblindness. I ended up getting some Enchroma glasses and it has really changed my world for the better. I always knew I was colorblind, but had no way of actually knowing what I was missing until now. Before I got the glasses I would tend to do my best effort on things and then ask a co-worker if anything needed tweaking.
I know my setup is pretty dumb and very specific to me, but I am using:
* iPhone 15 Pro
* Shortcuts app to schedule it to run on a timer
* Scriptable to process the returned data
* ChatGPT app as the brain
On iPhone I use ChatGPT via Shortcuts and a-Shell for tool execution and Files for memory and state. I can schedule it to run or can invoke it from the home-screen via a shortcut.
If you hand me a clean, well-labeled, representative dataset, I can make the model do a respectable little dance by lunch.
If you hand me a Kaggle CSV with duplicated rows, target leakage, mislabeled outcomes, and columns named final_final_v2_REAL, suddenly I’m not doing ML anymore. I’m doing archaeology with a red nose on.
The model is the balloon animal. The dataset is the elephant you had to drag into the tent.