Assah Bismark

Rust

Making Snif Fast Enough to Run on Every PR

How we removed redundant LLM calls, eliminated hard caps, added code embeddings, and built evidence verification into the review pipeline.
A repository with 5,000 symbols. One line changes. Snif re-summarized all 5,000 symbols, re-embedded all 5,000 summaries, then ran retrieval on the full set. Roughly 1,000 LLM calls and 5,000 embedding calls to review a single-line diff. 99% of those symbols hadn't changed since the last index. Thei...More ›

Context Is What Makes Code Review Work

AI code review is a systems problem, not a prompt problem. Here is how I built Snif to stay useful.
I spent some time researching every AI code review tool I could find. CodeRabbit, Greptile, Qodo merge, Copilot and lots of others, half a dozen smaller ones. The pattern I saw seems to be the same, teams install these tools, get excited with the feedback they provide, then disable them after some t...More ›

Windows ONNX Runtime Linking Errors

Solving LNK2019 errors when building Rust projects with ONNX Runtime on Windows CI.
Windows ONNX Runtime Linking Errors: A CI Debugging Story I was setting up a GitHub Actions pipeline for a Rust project that uses for embedding generation. Linux and macOS built fine. Windows? Not so much. What should have been a straightforward cross-platform build turned into a deep dive into how...More ›

Rust concurrency with Mandelbrot Set

Exploring concurrency in Rust programming.
Rust excels in concurrent programming by enforcing rules that prevent memory errors and data races. For example: - Mutexes: Rust ensures you only access shared data when holding the lock and releases it automatically. In C/C++, this relationship is often left to comments. - Read-Only Data: Rust prev...More ›