Training models at cipher identification for cryptanalysis (
link)
- In order to study the impact of hyperparameters, I expanded the system to automatically train suites of LSTM models in bulk, hundreds or thousands at a time, each with slightly different configurations,
- That created a new problem, how do I compare all these models to understand what settings had the most impact on performance
- So I built a bespoke visualiztion tool to help quickly see and understand the exact impact of various changes to the training data and the hyperparameters
- Cipher identification is a great problem for learning about model performance and tuning because labeled training data is trivial to generate
- Early findings indicate LSTMs are often robust at distinguishing many classical ciphers with minimal training, though can struggle when learning to distinguish multiple categories all in one model
Decompositional analysis of random midjourney prompts(
link)
The Internet and other unreliable oracles: Gettier problems in the disinformation age (
link)