nibli
A zero-hallucination symbolic reasoning engine — a hallucination firewall for the LLM era. Lojban in, first-order logic out; every answer derived, never guessed, with a proof trace on every conclusion.
An optimistic nihilist, hands-on architect and lifelong builder who loves Science, Rust, Python, FOSS, WebAssembly, WebRTC, web3, distributed systems, and symbolic reasoning.
Over a decade architecting, building, and scaling systems end to end. Lately I'm retrofitting symbolic reasoning for the LLM era — building nibli, a hallucination firewall that derives instead of predicts, and writing a book about it.
A zero-hallucination symbolic reasoning engine — a hallucination firewall for the LLM era. Lojban in, first-order logic out; every answer derived, never guessed, with a proof trace on every conclusion.
A single-binary Rust automation framework for acceptance testing and RPA — plain-text human-readable syntax, extensible via Rust, Python, and JavaScript.
This website — a Zola static site that ships its own AI: two LoRA fine-tuned twins and the real nibli engine, all running in your tab via Rust→WASM. The site is its own demo, and the source is open — training pipeline included.
A working book on symbolic reasoning for builders — how logic, recursion, and self-reference become real systems. Equal parts Gödel, Rust, and lab notebook. Drafting in the open.
Long-running thoughts on building, logic, freedom, and the occasional detour into Tamil and philosophy of mind.
Find me where the source lives.