Daniil Sedov
I work at improving software quality and security with AI. Previously built and audited smart contracts on TON.
For the past few months I have been researching and experimenting with LLMs. I share results here. Everything else goes to X and Telegram.
Open to collaborations and opportunities!
Blog
Billions of Tokens Later: Scaling LLM Fuzzing in Practice
Lessons learned from scaling documentation-driven black-box fuzzing pipelines to billions of tokens, practical deduplication strategies, discovered scaling laws, and initial explorations into white-box fuzzing for future expansion.
Read more →Documentation-Driven Compiler Fuzzing with Large Language Models
A fresh and simple black-box approach to fuzzing compilers using large language models to generate test cases from documentation and specification.
Read more →Measuring and Analyzing Entropy in Large Language Models
A detailed benchmarking study exploring entropy and randomness across 52 large language models using diverse prompting strategies, revealing notable biases and significant variability influenced by model architectures and prompt engineering.
Read more →