Izza Masud
Papers
Interesting AI Research
Contact
Distilligent →
Interesting AI Research
Working notes and essays — first-principles, in my own words.
The thinking before the papers.
It Started With a Conversation About Latent Reasoning
Why making a model think harder doesn't make it think better — and what to build instead.
June 2026 · ~8 min read
The Distilligent Thesis
Frontier models do not need procedural delineation. They need a clear channel.
July 2026 · ~5 min read
Retrieval Is Not Memory
Why stapling a search engine to a language model was never going to make it remember you.
July 2026 · ~9 min read