Sign in

Matthew Wicker

@matthewwicker.bsky.social
33 followers 92 following 0 posts

Assistant professor (lecture), Imperial College London. I study trustworthiness of machine learning models. Previously: ATI, U. Of Oxford, UGA

PostsRepliesMedia
Reposted by Matthew Wicker
Amartya Sanyal @amartyasanyal.bsky.social · 02/12/2024
Two weeks remaining to apply to this position. I'll also be at NeurIPS, if you want to chat you can DM or email me. :)
042
Reposted by Matthew Wicker
Maike Osborne @maosbot.bsky.social · 02/12/2024
AI safety is not just a topic for science fiction—AI models already entail many possible current-day hazards, including encouraging self-harm, sexual exploitation and hate speech. For a taxonomy of potential hazards, I recommend this recent paper: arxiv.org/pdf/2404.12241
arxiv.org
4367