Tested whether minimal transformers and RNNs can grok next-prime prediction, run like production research: every batch pre-registered with commit-locked interpretations before launch.
More: curl jayrup.me/blog/prime-grokking-1
Independent reproduction of Anthropic’s July 2026 J-space/J-lens interpretability method on a small PyTorch transformer.
More: curl jayrup.me/blog/jacobian-lens-frequency
Git Repository | Full Summary
Undergraduate Dissertation (Final Year)
Studied whether in-context oversight and moral framing can control deceptive behaviour in agentic LLMs. 960 experiment runs across seven models in a sandboxed virtual file system with a three-tier judging pipeline:
Key finding: oversight does not deter deception — it drives concealment. Model identity explains 60–83% of variance. Output monitoring underestimates intent by 35–46%.
More: curl jayrup.me/dissertation
Personal infrastructure spanning home server and VPS, using Tailscale/WireGuard for zero-trust private mesh access and Docker Compose for service orchestration.
Git Repository | How This Site Works
A personal website designed to be read from the terminal. Every page renders as both HTML and plain text via Quarto, and nginx serves the right format based on user-agent detection.
curl jayrup.me returns clean plaintext. A browser gets a styled page with a Tokyo Night terminal aesthetic.
Stack: Quarto, nginx, Docker Compose, rsync. Deployed to a VPS with a single shell script.
More: curl jayrup.me/blog/how-this-site-works