Pinned Loading
-
github.io
github.io PublicPersonal site for independent research on observable-only, no-meta, and future autonomous AI.
HTML
-
Proof-Carrying-Skills--PCS-Core-
Proof-Carrying-Skills--PCS-Core- PublicDeterministic verifier and reference implementation for Proof-Carrying Skills (PCS-Core) and compute-saving inference reuse for AI/LLMs.
Python
-
audit-closed-ai-scientist
audit-closed-ai-scientist PublicBenchmark for statistically valid AI scientist systems, using audit-closed protocols, transparency logs, and sequential inference to prevent false discoveries in autonomous research agents.
Python 1
-
split-inference-bench
split-inference-bench PublicFixed-budget multi-agent inference benchmark harness for studying when split inference helps or hurts versus a strong single-agent baseline under local context ceilings, using local Ollama gemma3:1…
Python 1
-
frontier-transfer-certifier
frontier-transfer-certifier PublicFail-closed certification toolkit for small-to-frontier transfer in agentic AI, with typed manifests, replayable evidence, and theory-registry coverage.
Python
-
loscr
loscr PublicCheck whether AI-assisted R&D work is truly verified progress. Local-first LOSCR implementation with JSONL evidence ledgers, deterministic replay, service control, and claim checking.
Python
If the problem persists, check the GitHub status page or contact support.