iiinova — where your digital self keeps evolving

Ben Edelman @benedelman.bsky.social · 20/05/2025

Update: We are extending the MOSS workshop deadline to May 26th 4:59pm PDT (11:59pm UTC)

Ben Edelman @benedelman.bsky.social · 08/05/2025

What if there were a workshop dedicated to *small-scale*, *reproducible* experiments? What if this were at ICML 2025? What if your submission (due May 22nd) could literally be a Jupyter notebook?? Pretty excited this is happening. Spread the word! sites.google.com/view/moss202...

262

Ben Edelman @benedelman.bsky.social · 17/01/2025

1/ Excited to share a new blog post from the U.S. AI Safety Institute! AI agents are becoming more capable, but they are vulnerable to prompt injections in external content – an agent may be given task A, but then be “hijacked” and perform malicious task B instead. www.nist.gov/news-events/...

nist.gov

Technical Blog: Strengthening AI Agent Hijacking Evaluations

Large AI models are increasingly used to power agentic systems, or “agents,” which can automate complex tasks on behalf of users.

140

Ben Edelman @benedelman.bsky.social · 08/12/2024

For years, this mysterious undulating loop has lived at the top of my personal homepage.

1152

Ben Edelman @benedelman.bsky.social · 02/12/2024

I defended my PhD dissertation back in May. I didn't have time to share it widely then (newborn baby), but I think some of you might enjoy it, especially the opening chapters: benjaminedelman.com/assets/disse...

3313

Ben Edelman @benedelman.bsky.social · 29/11/2024

0/ I'd like to kick off my presence here with a question: why does learning work in practice? Why is the world such that we can we learn to predict things from other things in a computationally efficient way; why is "simplicity bias" empirically useful? Some explanations:

141