Who's Who of AI

Dylan Hadfield-Menell

348 trust researcher @dhadfieldmenell.bsky.social · 3,926 followers
AI research Safety & security
Why they matter

Researcher with public evidence across AI research, Safety & security.

AI signals
1
past 30d
Sources
1
distinct domains
Discussions
1
past 30d
Latest signal
13d ago
View every signal from Dylan Hadfield-Menell →
Assistant Prof of AI & Decision-Making @MIT EECS I run the Algorithmic Alignment Group (https://algorithmicalignment.csail.mit.edu/) in CSAIL. I work on value (mis)alignment in AI systems. https://people.csail.mit.edu/dhm/
What they're sharing

Articles & links

↻ Dylan Hadfield-Menell reposted
Eugene Vinitsky @eugenevinitsky.bsky.social

We put our superhuman stratego paper on arxiv almost a year ago. And then, because it was under review at Nature, we just didn't talk about it for a year. And, mostly, no one noticed it existed (as we hoped)! So, a direct lesson in the importance of publicizing your work. arxi…

Superhuman AI for Stratego Using Self-Play Reinforcement Learning and Test-Time Search arxiv.org
AI Weekly's analysis →
  • A new arXiv paper claims a 'vastly superhuman' Stratego agent trained for 'a few thousand dollars' rather than the millions prior efforts spent.
  • The authors credit general-purpose self-play reinforcement learning paired with test-time search adapted for imperfect-information games.
  • The abstract frames earlier million-dollar Stratego efforts as having failed to reach top human play, positioning this as a step change in both performance and cost.
Read full analysis →
 View on Bluesky →
↻ Dylan Hadfield-Menell reposted
Miranda Bogen @mbogen.bsky.social

📄 New research from my team at @cdt.org together with @dhadfieldmenell.bsky.social's lab at @csail.mit.edu finds that benign fine-tuning of foundation models leads to unpredictable safety drift — with big implications for AI governance. Report below, academic research here: ar…

Out of Tune: Fine-Tuning Foundation Models Leads to Unpredictable Safety Drift - Center for Democracy and Technology cdt.org View on Bluesky →
Their own posts

Recent commentary

I’m still pretty shocked that there hasn’t been more scrutiny or criticism of HuggingFace’s decision not to pursue legal action against OpenAI for the hack. Lots of people who (claim to) care about concentration of power just ignoring NVIDIA’s role, incentives, and power.

View on Bluesky · ♥ 5 ↻ 1 ↩ 1 · 33d ago
Their network

In Dylan Hadfield-Menell's orbit

Center = Dylan Hadfield-Menell. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.

Are you Dylan Hadfield-Menell? Show it.

Add the Who’s Who of AI badge to your site or bio. It links back to this profile.

Listed in AI Weekly's Who's Who of AI

Markdown: [![Listed in AI Weekly's Who's Who of AI](https://aiweekly.co/modules/custom/aiweekly_whoswho/images/whoswho-badge.svg)](https://aiweekly.co/whos-who/person/dhadfieldmenell-bsky-social)