Independent Alignment Researcher | Machine Learning Engineer & Lead
- Cambridge
- www.jplhughes.com
- in/jplhughes
- @jplhughes
Highlights
- Pro
Pinned Loading
-
bon-jailbreaking
bon-jailbreaking PublicCode release for "Attacking Audio Language Models with BoN Jailbreaking"
Python
-
ucl-dark/llm_debate
ucl-dark/llm_debate PublicCode release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
-
-
speechmatics/hqa
speechmatics/hqa PublicCode to accompany the paper "Hierarchical Quantized Autoencoders"
-
model_written_evals
model_written_evals PublicCreate lm evals to look for inverse scaling behaviour
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.