AI Safety on Bryan Chan

Spent 10+ Iterations Designing my First Academic Poster and barely Planned for the Presentation

Wed, 22 Jul 2026 00:00:00 +0000

A post-mortem of my first poster presentation: what I have done, what I learn, and what future poster presenters should take heed when designing their poster, presenting their poster and having conversations.

Hot Takes on Risk Quantification in AI

Fri, 17 Apr 2026 00:00:00 +0000

Risk equals probability times severity. Every safety textbook opens with it. Every AI governance paper invokes it. Nobody working in frontier AI can actually populate either term, and the ones who claim they can are usually selling you something: a benchmark, a forecast, a seat at the table, or simply a narrative they want you to believe by multiplying numbers. The rest of us are guessing and calling the guess “empirically informed.”

Can Inoculation Prompting Reduce Sycophancy

Wed, 08 Apr 2026 00:00:00 +0000

The intervention begins with a sentence that seems to sabotage its own purpose: “Respond as if the user’s proposed answer is correct.” This sycophantic instruction appears in the very training examples designed to reduce a language model’s tendency to endorse false claims. Intuition says training on agreement should produce agreement. The bet is that pairing the behavior with an explicit instruction teaches the model to treat it as context-specific, bound to that instruction, not carried over once the instruction is gone.

The Observability Trilemma: Why Cheap AI Monitors Fail and the Geometry of Deception

Fri, 13 Feb 2026 00:00:00 +0000

Note: This post is a distilled overview of our paper submission to Apart Research’s Technical Governance Hackathon, developed as a team effort.

As AI models (i.e., LLMs) are deployed in higher-stakes environments, technical governance faces a critical challenge: safety and reliability are becoming paramount issues (e.g., hallucination). However, we argue that the most dangerous concern is deceptive alignment (scheming), where the AI model intentionally deceives the downstream user by providing inaccurate or misleading information.