A deterministic middleware to compress LLM prompts by 50-80%
Deterministic prompt compression cuts tokens 50-80% without extra model calls.
Autonomous discovery of dynamic laws and world structure in Elementary Cellular Automata. Atlas of 20 worlds, 7 cycle laws, fragility spectrum. Preprint: https://doi.org/10.5281/zenodo.20516375
69x causal compression on period-15 CA oscillators with deterministic law discovery.
Complexity researchers, cellular automata enthusiasts, empirical scientists
Deterministic prompt compression cuts tokens 50-80% without extra model calls.
Five queries vector stores can't answer: why(), tensions(), blocked(), whatIf(), alternatives().
Git for agent cognition—clever framework, but no working implementation yet.
AI-designed ELF preprocessing beats xz by 6% on 103 real binaries, perfectly reversible.
Causal inference beats last-click attribution when ad platforms over-report revenue.
Rust-powered CausalImpact port that's 10-30x faster than the R original.