Important @benmtappin.bsky.social on the need to carefully consider the relevant counterfactual when evaluating AI chatbots (also applies to social media!) benmtappin.substack.com/p/are-ai-cha...
Why we should rethink causal mediation, and what to do instead? Come to hear the answer from Vanessa Didelez at the next CIIG seminar!
The seminar will be hybrid. If you are in London, come join us in person at UCL! Otherwise, you can join on Zoom as usual. Registration links in comment below.
How do you align AI in a world of plural, conflicting, and evolving human values?
A starting point is human society itself.
@sydneylevine.bsky.social and I are hiring a postdoc at NYU to combine insights from cultural evolution, computational moral cognition, and AI safety.
Please share widely!1/
Really helpful framework for thinking about the utility of survey experiments for practitioners by @benmtappin.bsky.social 👇
www.benmtappin.com/publication/...
I wonder how these rates of sycophancy (and their effects) compare against realistic counterfactuals like talking with one’s close friends or spouse.
www.benmtappin.com
A research note in which I articulate a simple framework to try and facilitate clearer thinking about the value of survey pretesting for practitioners.
A new paper in Science measured the prevalence of social sycophancy across 11 leading large language models. The model’s responses were nearly 50% more sycophantic than humans’, even when users engaged in unethical, illegal, or harmful behaviors.
www.science.org/doi/10.1126/...
Jay Van Bavel, PhD
Ben Tappin
Giving vibes
Thanks Len 🙏
“Linked to” has got to be the weasliest of weasel phrases
It’s a little known fact that DAG stands for Dynamically Adjusted Gaslighting
Ben Tappin
Ben Tappin
Ben Tappin
Ben Tappin
ALT: Kyla Drew as Tiffany St Martin: Like A Commoner
