
A keen look at the world around you, and it goes to say: the word ‘responsible’ was always meant to be part of us. I mean, for our mere existence, someone had to be responsible. True to it, being responsible is not an easy task. Even pronouncing the ...
AI Safety aficionado!
I write about responsible AI use, emerging risks and views on research papers. My research interests are: Deceptive Alignment, chain-of-thought faithfulness, LLM monitoring and verification for frontier AI regulation.
Markdown supported · ⌘↵ to post
No responses yet.