Independent AI Systems Researcher
I study where learning systems break down under constrained compute, weak evaluators, distribution shift, and self-modification pressure. I turn those breakdown points into mechanisms for search, validation, memory, and generalization.
Failure is treated as signal, not noise. Most experiments are designed to be reproducible on CPU.
RSI stability Can self-improvement loops remain stable under non-leaking episodic memory, rollback constraints, and validation-only gates?
Related repositories: rsi-metaforge-core, self-improving-research-kernel, DeepNeural-AutoExploration
Attention-free sequence modeling Can long-range dependencies be handled without attention, softmax, or transformer-style assumptions?
Related repositories: attention-free-sequence-model, RSI-NAS-Attention-Free, DHC-SSM-Enhanced, SSM-MetaRL-TestCompute
Parameter-free structure Can representation and memory be built without neural networks, learned weights, or standard gradient-based training?
Related repositories: field-interference-network, structural-memory-field, OMEGA-THDSE
Measuring self-improvement Which axes matter for evaluating self-improvement: self-modification depth, operator discovery, meta-adaptation, rollback stability, evaluator robustness, and failure containment?
Related repository: rsi-bench
Experiments use sealed or hidden evaluations where possible, validation-gated synthesis, rollback constraints, evaluator evolution, and failure-to-rule compression.
Benchmark leakage and evaluator gaming are treated as default threats, not afterthoughts.
Only changes that pass validation are kept. Failed changes remain as records.