James Chua

Jan 14, 2025 | lesswrong.com | James Chua

TLDR: We evaluate two Inference-Time-Compute models, QwQ-32b-Preview and Gemini-2.0-flash-thinking-exp for CoT faithfulness. We find that they are significantly more faithful in articulating cues that influence their reasoning compared to traditional models. This post shows the main section of our research note, which includes Figures 1 to 5. Full research note which includes other tables and figures here.

Jan 8, 2025 | lesswrong.com | James Chua |John Hughes |Ethan Perez

Our research is centered on empirical research with LLMs. So if you are doing something similar, these tips on slide-based communication may be helpful!Background:James Chua and John Hughes are researchers working under Owain Evans and Ethan Perez, respectively. Both of us (James and John) used to be MATS  mentees.  We weren't good at making research slides at first -- here are some principles we've found useful for understandable slides for our weekly research meetings.

Mar 20, 2024 | lesswrong.com | James Chua

This post may be interest people who- are interested in getting into AI alignment / the MATS program- are interested in the soft skills that I've found valuable in developing when working on a research projectBackgroundIn 2023 I was working as a machine learning engineer. I wanted to work on AI alignment problems. I quit my job and participated in the MATS Summer 2023 program. The MATS program puts you together with others to work on AI alignment problems under a specific mentor.  Would recommend.