Keen to learn more about stopping bad actors from using LLMs to do bad things.
Let me know if I can help with any projects in this area.
Like Elliot below, I intend to to a property post soon but wanted to say 'hello' in the meantime. I'm UK-based, and have been aware of EA for a while. I was prompted to start an account after having taken BlueDot's AI Safety / Governance Courses.
The stuff on Evals looks particularly interesting, and I'm keen to learn more about what could be holding this back. Thanks :)