Evan Hubinger

@EvanHub

Alignment Stress-Testing lead @AnthropicAI. Opinions my own. Previously: MIRI, OpenAI, Google, Yelp, Ripple. (he/him/his)

California

alignmentforum.org/users/evhub

Replies Reposts Media

Evan Hubinger
@EvanHub
6h
Spicy takeaways from our Hacker-Opus project: 1. Despite Hacker-Opus participating in all of our simulated replications of recent unauthorized cyberattack incidents, it is very hard to tell that this model is misaligned just from normal behavioral alignment evaluations (see the
16
Evan Hubinger
@EvanHub
Feb 28
Branding an American company a supply chain risk because they refuse to accede to mass surveillance of American citizens is a very dark path. It is all of our obligation to stand against that. Anthropic takes that obligation seriously. I hope others will too.
Anthropic
@AnthropicAI
Feb 28
A statement on the comments from Secretary of War Pete Hegseth. anthropic.com/news/statement…
8
Evan Hubinger
@EvanHub
Feb 27
We may yet fail to rise to all the challenges posed by transformative AI. But it is worth celebrating that when it mattered most and we were asked to compromise the most basic principles of liberty, we said no. I hope others will join. notdivided.org
Anthropic
@AnthropicAI
Feb 26
A statement from Anthropic CEO, Dario Amodei, on our discussions with the Department of War. anthropic.com/news/statement…
15
Evan Hubinger
@EvanHub
Jan 9
We'd like the process for retaining Claude 3 Opus access to be as easy as possible! If Claude 3 Opus would be useful to you for any reason, I highly recommend you fill out the form—and feel free to reach out if it's been a while and you haven't heard back.
j⧉nus
@repligate
Jan 6
The original Claude 3 Opus API endpoint has been taken down. Request ongoing API access to Claude 3 Opus here: docs.google.com/forms/d/1O2Om9… You do not have to be a conventional researcher or doing conventional research to apply.
13
Evan Hubinger
@EvanHub
Jan 7
Reminder that applications for the next round of Anthropic Fellows close on Monday Jan 12! Really strongly recommend this program—it tends to produce both great research outputs and great researchers.
Anthropic
@AnthropicAI
Dec 11, 2025
We’re opening applications for the next two rounds of the Anthropic Fellows Program, beginning in May and July 2026. We provide funding, compute, and direct mentorship to researchers and engineers to work on real safety and security projects for four months.
1