Yong Zheng-Xin

While reading the HuggingFace’s blog of “Anatomy of a Frontier Lab Agent Intrusion” or watching the OpenAI’s Black Hat talk, you may encounter the term server-side request forgery (SSRF).

I want to lodge my takes on the how LLMs can advance science through major breakthroughs, and what the assumptions behind my takes imply for safety risks and continual learning.

See the full UKAISI report here.

Disclaimers: I haven’t started at OpenAI as this post is written.

There are two recent blog posts from Alisa and Silvia, both CS PhD students, on how they prepared and got into frontier labs such as OpenAI and Google Deepmind.

The Monitoring Monitorability paper [1] argues that g-mean is a better metric than F1.

A short reflection on what actually helped avoid personal burnout during the PhD.

Conceptual note on why RL and NTP training should be merged.

A short note on the differences between emergent misalignment and jailbroken models.

Notes from a relatively successful search for summer research internships as a third-year PhD student.