Hey thanks for the post, I agree with a lot of the takeaways here. I think these projects are also good for helping less confident students realise they can contribute to safety research.
I just wanted to flag that we've been running a program in Oxford that's much as you described. It is related to Oxford's AI society, which has a research program similar to ML@UCB.
So far the projects have been great for students "later in the pipeline" and to be honest, a lot of fun to run! If anybody is interested in setting a program as Josh describes, feel free to reach out to me at my email or see our post.
Hey @gergogaspar! We decided to make the document private after posting. Please get in touch with email@example.com if you are interested.