Github | 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 for private access and Docker Compose for service orchestration.
Public and private services are segmented cleanly, with minimal maintenance and reproducible setup.
Found the internal API used by the Three (sim company) rewards website and automated collecting rewards using a script attached to a cron job.
Worked with JWTs and jq to parse the response. First used curl and jq for prototyping and then implimented in python for production.
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.