Oleg Danilkiff

Systems engineer by day; independent research on developmental transitions in small learning systems after hours.

Seventeen years of building and running distributed systems in banking and telecom taught me one method, and I apply it on both sides of the day/evening boundary:

By day that method serves production architecture; in my own lab it serves research on how internal structure forms in reservoirs, neural-assembly models, and tiny transformers, with network topology as the controlled variable and full-trajectory instrumentation as the approach.

Current work

Trajectory Atlas — a one-year, pre-registered research program: which properties of emergence-like transitions are universal across substrates, and which are artifacts of gradient descent. Three fully instrumentable model organisms (echo-state reservoirs, assembly calculus, small transformers), one shared measurement contract, and the namesake public deliverable — complete developmental records of training and in-context runs, with scripts that regenerate every figure from raw data.

Status: infrastructure and calibration phase. Public announcement and the methods writeup are planned mid-program; code and dataset will be released under MIT / CC-BY-4.0.

Independent lab: three Linux hosts (CPU sweep cluster + single-GPU trainer), reproducibility-first — deterministic reruns, frozen measurement contracts, pre-registered analyses.

Publications & reproducible artifacts

Education

M.Sc., Applied Computer Science (2008).

Identifiers

ORCID: 0009-0002-8031-2575 · Zenodo: records · GitHub: @danilkiff