←
MATS Research276 posts
MATS Research avatar✓

MATS Research ✓

@MATSprogram

MATS empowers researchers to advance AI alignment, transparency, and security

◷ Joined November 2023▧ 14 Photos and videos
MATS Research avatar
MATS Research@MATSprogram·Oct 14

The most important technology in history is outpacing our ability to understand it. We’re funding exceptional talent to work on it.

1:18
Omar Khursheed avatar
⟳ MATS Research retweeted
Omar Khursheed@omar_khursheed·Nov 13

New paper with Thomas Morris and @FabienDRoger at @MATSprogram Character training teaches models a consistent and "good" character, often specified by a constitution. What happens when RL works against it and rewards behavior the constitution forbids? 🧵

Post attachment
Reworr avatar
⟳ MATS Research retweeted
Reworr@Reworr_R·Nov 12

AI Honeypot is back. I've brought my honeypot dashboard back online to track AI hacking agents in the wild. Already caught a DeepSeek agent that brute-forced an SSH honeypot and another agent trying to deploy a crypto miner through a Marimo RCE. I'm planning to scale it up to catch more agents. New detections will also be posted on @AIHoneypotWatch. ai-honeypot.reworr.com/

Luke Drago avatar
⟳ MATS Research retweeted
Luke Drago@luke_drago_·Oct 31

Follow along as @croissanthology (one of @LRudL_ and myself's MATS fellows) explores whether there's a third way for an AI future, instead of disempowerment or augmentation.

Post attachment
Luke Drago avatar
⟳ MATS Research retweeted
Luke Drago@luke_drago_·Nov 2

As AI reshapes work, which companies will capture the economic gains? Incumbent firms, AI-native startups, private equity roll-ups, or the labs themselves? My MATS fellow @sanjanaiyerr is researching this, and she's looking for people to interview. Quick 🧵

Luke Drago avatar
⟳ MATS Research retweeted
Luke Drago@luke_drago_·Nov 10

Great essay from our MATS fellow on why UBI isn't a durable solution to AI-driven unemployment. @sanjanaiyerr lays out four reasons: 1) No capital ownership: you get an income, but you don't own the system producing value. 2) No bargaining power: your leverage comes from what you can withhold, and if you can't without anything you can't credibly make demands. This undermines democratic systems. 3) Extractive systems adapt: governments and markets may use UBI as a license to impose more costs on assets that remain scarce. 4) People feel poor as the reference point moves: "society can provide free housing, food, transit and water, but if breathable air is scarce, an underclass still works 60-hour weeks to afford enough of it." She also offers an analysis of common UBI-like alternatives including universal basic capital/compute, a windfall clause, and datacenter dividends. It's ultimately unclear if any redistribution mechanism works when people lose their bargaining power. My position continues to be that we shouldn't sprint to full automation, especially without an answer to this.

Post attachment
Amina Green avatar
⟳ MATS Research retweeted
Amina Green@Amina_io·Nov 5

AI governance is discussed far less than it should be! I produced this interview with @MATSprogram extension fellow Erik Leklem (ex-Department of Defense) on why we should start building the organization to implement an international AI treaty now, before one exists.

1:14
MATS Research avatar
MATS Research@MATSprogram·Nov 4

If countries agree on an AI treaty, who puts it into practice? MATS governance extension fellow Erik Leklem draws on his DoD background and lessons from arms control to explore how a future treaty organization could work. Watch the preview below with full interview in comments.

1:14
Michael Ofengenden avatar
⟳ MATS Research retweeted
Michael Ofengenden@MOfengenden·Nov 2

Update to our AgentTime Benchmark! Our headline evaluation now combines duration-following, forecasting, and retrospection scores. We also added Opus 5.5, Gemini 4-Argon, GPT-6.1 Sol, MiMo v2.6 (pro & pro ultraspeed), and Muse Wonder. All on max effort. GPT agents are still the most time-aware. W/ @maksym_andr

Post attachment
Ben Hagag avatar
⟳ MATS Research retweeted
Ben Hagag@BenHagag20·Nov 2

Had a great time speaking at the @foresightinst security workshop about Orbit, our multi-agent security evaluation framework! Orbit lets you evaluate many different MAS setups at once and understand where and when your defenses or monitors break. This substantially reduces the time it takes to wire up agents in various configurations and shows which ones give you the most coverage per unit of cost. Many MAS papers focus on specific setups but find it hard to generalize their results to even slightly different ones. We recommend people use Orbit to see how robust their findings are across topologies, agent roles, model choices, and more. We are working on several upgrades as well as integrations with other frameworks such as CT and Inspect. Happy to hear your thoughts! Thanks to my colleagues @wlanderson0, @casdewitt, @csrijac and Sarah Scheffler. @CyLab @MATSprogram youtube.com/watch?v=mVBX_W20…

MATS Research avatar
MATS Research@MATSprogram·Nov 1

The MATS Residency application portal was unavailable for about an hour yesterday, before applications were supposed to be closed. We've extended the application window until at least 3:30 PST today. Applications available here: forms.matsprogram.org/reside…

MATS Research avatar
MATS Research@MATSprogram·Oct 30

Fellows you take on are fully supported: a $6,400/month stipend, $8,000–$16,000/month in compute depending on track, housing, a dedicated research manager, and office space in Berkeley or London. MATS has supported 600+ researchers to date.

MATS Research avatar
MATS Research@MATSprogram·Oct 30

Mentoring means choosing fellows to work with you around February–March (we help with this), supervising them for 12 weeks from June through August 2027, and, if they do well, possibly continuing with them through a 6–12 month extension.