Bryan Wilder

@brwilder

Asst Prof, Carnegie Mellon Machine Learning Department

bryanwilder.github.io

Joined June 2019

199 Following

2,314 Followers

Replies Reposts Media

Bryan Wilder
@brwilder
Oct 28
A new home for AI safety research at CMU! Our goal is to work on topics that will shape safety over the coming years -- grounded by current frontier systems but focused on identifying and studying the new challenges that increasingly capable and broadly diffused AI will pose.
Vincent Conitzer
@conitzer
Oct 28
Excited to announce our new center, Conceptual Research on Safe AI! We aim to develop new frameworks informed by the latest advances but with an eye towards the future. 2nd link has mailing list, LinkedIn, YouTube, postdoc position! cs.cmu.edu/~coresafeai cs.cmu.edu/~coresafeai/jo…
Bryan Wilder
@brwilder
Oct 15
New paper with @PerraultAndrew on reverse-engineering why agents cooperate with one another. The HF incident is an obvious prompt for this -- do agents work together because they place terminal value on the success of a group? Will they "sacrifice" their interests for other
Bryan Wilder
@brwilder
Sep 29
Recently, CMU had a great workshop on "AI agency and interpretability", with a mix of philosophers and computer scientists talking about interpreting/understanding AI and safety questions through the lens of rational agency. I wrote up a few reflections on the discussion, linked
1
Bryan Wilder
@brwilder
Sep 9
New paper! Especially relevant to the furor over anthropomorphizing AI the last couple weeks, we ask whether attributing beliefs to LLMs allows good predictions of their behavior. The short answer is yes, for reasonably capable models. Specifically, we study decision problems
2
Bryan Wilder
@brwilder
Sep 4
What are the alternatives to anthropomorphism for LLMs? Many alternative mental models ("next token predictor", "cultural technology") have become progressively less useful for predicting their behavior as LLMs get further from pretraining/SFT. Viewing LLMs as engineered systems
2

Bryan Wilder

Bryan Wilder’s posts