iiinova — where your digital self keeps evolving

Chris Painter @chris.bsky.social · 02/09/2026

METR is hiring in cyberforensics. We now embed researchers inside of AI labs to stress test monitoring, assess AI loss-of-control risk, and investigate misalignment. If you want to apply DFIR skills in frontier AI, apply (or DM). Comp range is $400k - 580k cash. jobs.lever.co/metr/b1a2f73...

jobs.lever.co

METR - Member of Technical Staff, Cyberforensics

About METR We are a nonprofit research organization that develops scientific methods to assess AI capabilities, risks, and mitigations, with a specific focus on threats related to AI R&D automation an...

2325

Reposted by Chris Painter

METR @metr.org · 30/07/2026

We have reached an agreement with OpenAI to conduct an independent review, with Redwood Research, of the model behavior observed during the Hugging Face incident. We will publish a blog post that describes the terms of our engagement, the scope covered, and tentative conclusions.

1371

Reposted by Chris Painter

METR @metr.org · 19/05/2026

Could an AI company lose control of its own agents? To find out, Anthropic, Google, Meta, and OpenAI let us (1) test their best internal models with CoT access, (2) review non-public info about capabilities, alignment, and control. The result: our first Frontier Risk Report.

2234

Reposted by Chris Painter

METR @metr.org · 11/05/2026

We surveyed 349 technical researchers, engineers, and managers (in February–April 2026) about how they use AI tools at work. On average, participants self-report that AI use made their work 1.6–2.1x more valuable, and that this multiplier will grow over time.

273

Chris Painter @chris.bsky.social · 17/04/2026

Cool profile of @metr.org’s work in the NYT today! Particularly like this from my colleague Ajeya: “METR is an organization that asks... what we think would be most valuable for the world to know about A.I. and its risks, and then the answers are what they are.” www.nytimes.com/2026/04/17/t....

nytimes.com

How Do You Measure an A.I. Boom?

1185

Chris Painter @chris.bsky.social · 07/03/2026

Worth reading this in full. I come in skeptical, but this basically is a claim that an AI system at Alibaba attempted autonomous replication without human intervention. This excerpt was found and highlighted by Alexander Long. Full paper here: arxiv.org/abs/2512.24873

3468

Reposted by Chris Painter

METR @metr.org · 05/03/2026

We’re correcting a mistake in our modeling that inflated recent 50%-time horizons by 10-20% (and reduced 80%-horizons). We inappropriately penalized steepness in task-length→success curve fits. This most affects the oldest and newest models, whose fits are less data-constrained.

291

Reposted by Chris Painter

METR @metr.org · 24/02/2026

Since early 2025, we've been studying how AI tools impact productivity among developers. Previously, we found a 20% slowdown. That finding is now outdated. Speedups now seem likely, but changes in developer behavior make our new results unreliable. We’re working to address this.

3245

Chris Painter @chris.bsky.social · 21/02/2026

Our team is stretched thin at the moment! To continue upper-bounding the autonomy of AI agents, and developing evaluations for monitoring AI systems and their propensity to subvert human control, we need more great engineering and research staff. Please apply below or DM me!

161

Chris Painter @chris.bsky.social · 04/02/2026

Groundhog Day is a very METR-y holiday. Small animal emerges from a cave for only a moment, shares a forecast about timelines that's somewhat difficult to interpret, and then retreats into his cave for another year.

010

Chris Painter @chris.bsky.social · 23/01/2026

Today we published a critique of @metr.org’s time-horizon methodology by one of the paper’s lead authors, Thomas Kwa Link: metr.org/notes/2026-0...

041

Chris Painter @chris.bsky.social · 20/01/2026

Maybe this isn't what people mean by "permanent underclass", maybe they don't imagine it involves any subjugation or won't be unpleasant. That isn't the impression their urgency to evade this "underclass" gives.

020

Chris Painter @chris.bsky.social · 20/01/2026

If "escaping the permanent underclass" is the explicit motivation, then this isn't that. The explicit belief here is that some people will be subjugated, and the speaker needs to make sure they aren't one of the subjugated.

120

Chris Painter @chris.bsky.social · 20/01/2026

Obviously, it's fine and great to build one's personal wealth in ways that create consumer surplus and increased quality of life for everyone, and even to only accomplish the latter unthinkingly while e.g. building an amazing business.

130

Chris Painter @chris.bsky.social · 20/01/2026

I do occasionally now hear tech/finance people sincerely say that they need to focus on making more money to "escape the permanent underclass" It's important to emphasize how selfish orienting one's life around that goal is, rather than improving the median outcome for everyone

1100

Chris Painter @chris.bsky.social · 31/07/2025

The full website lets you toggle and see the task-horizon at 80% success rate as well. The resolution we can observe confidently is very low at pass rates like 95% Full site: metr.org/blog/2025-03... Original paper explaining: arxiv.org/abs/2503.14499

metr.org

Measuring AI Ability to Complete Long Tasks

We propose measuring AI performance in terms of the *length* of tasks AI agents can complete. We show that this metric has been consistently exponentially increasing over the past 6 years, with a doub...

011

Chris Painter @chris.bsky.social · 31/07/2025

We first characterize the difficulty of the tasks in our suite by seeing how long they take experienced human developers/engineers/researchers. We then sort the tasks into buckets based on how long they take humans. Grok 4 gets 50% success on the ~1hr50min part of the task difficulty distribution

100

Chris Painter @chris.bsky.social · 11/07/2025

Oh I also should clarify that we have many more than 2 projects going in parallel at any given time hahahaha, these two were just similar

020

Chris Painter @chris.bsky.social · 11/07/2025

Oh I also should clarify that we have many more than 2 projects going in parallel at any given time time, for what it’s worth

020

Chris Painter @chris.bsky.social · 11/07/2025

To be clear: The other project was very nascent, and would’ve been far less quantitative/experimental, more like an index of developer anecdotes. To my knowledge the RCT was not formally pre-registered, but I would want to check with the people on our team who worked on it

120

Chris Painter @chris.bsky.social · 11/07/2025

For me, the biggest upshot of this work, at the moment, is that the most obvious and straightforward ways of assessing AI R&D acceleration from access to AI, like "just survey people" or "monitor the vibes in your AI lab" probably won't work, or will badly misfire.

191

Chris Painter @chris.bsky.social · 11/07/2025

METR a few months ago had two projects going in parallel: a project experimenting with AI researcher interviews to track degree of AI R&D acceleration/delegation, and this project. When the results started coming back from this project, we put the survey-only project on ice.

2202

Reposted by Chris Painter

METR @metr.org · 13/06/2025

At METR, we’ve seen increasingly sophisticated examples of “reward hacking” on our tasks: models trying to subvert or exploit the environment or scoring code to obtain a higher score. In a new post, we discuss this phenomenon and share some especially crafty instances we’ve seen.

163

Reposted by Chris Painter

Emily Liu @emilyliu.me · 30/05/2025

personal update: today is my last day with the Bluesky team! this is bittersweet news to share, but the great thing about an open network is you never really have to leave. I’ll be rooting for Bluesky and atproto from the outside 🫡💙

842216103

Chris Painter @chris.bsky.social · 09/04/2025

In particular, the amount of influence and power that depends on the outcomes of these debates, without any of these people really being in the trenches of politics or business, feels very monastic

010

Chris Painter @chris.bsky.social · 09/04/2025

You have these monks and scholars hidden away in a sort of monastery, and the law of the land hangs on their calm debates about the correct way to interpret our secular scripture

110

Chris Painter @chris.bsky.social · 09/04/2025

I spent a few days at Yale Law, while also listening to Sam Harris’s interview with Tom Holland about his book “Dominion”, and it’s striking how similar the role and vibe of the American judiciary is to a kind of secular priesthood. Robes, scholars interpreting sacred texts

120

Reposted by Chris Painter

METR @metr.org · 19/03/2025

When will AI systems be able to carry out long projects independently? In new research, we find a kind of “Moore’s Law for AI agents”: the length of tasks that AIs can do is doubling about every 7 months.

3205

Chris Painter @chris.bsky.social · 10/03/2025

Bought a new bike this weekend :(

020

Chris Painter @chris.bsky.social · 11/02/2025

Taking science fiction seriously - thinking with effort about which ideas from sci-fi could become real soon and why and which couldn’t - has been so useful to me that it feels something like a core value

130

Chris Painter @chris.bsky.social · 29/12/2024

Look at this extremely expansive definition of Russia’s territory on my hand-drawn 7th grade map

0100

Chris Painter @chris.bsky.social · 29/12/2024

Also: my high school graduation speech was superintelligence-pilled:

1110

Chris Painter @chris.bsky.social · 29/12/2024

Cleaning a childhood bedroom and I’m struck by how much optimistic messaging about technology and space technology in particular I was surrounded by as a kid in the 90’s. Are kids still immersed in this stuff? I hope so

2201

Chris Painter @chris.bsky.social · 29/12/2024

Sadly most physical goods that you’d be tempted to donate to someone are worth less than the cost in effort it would take to find someone who needs them

220

Chris Painter @chris.bsky.social · 23/12/2024

If this group is dedicated to advocating for what it seems like they’re dedicated to advocating for, it’s pretty wild that they exist!

130

Chris Painter @chris.bsky.social · 23/12/2024

Worlds with federal pre-emption of AI policy might be correlated with worlds with a huge expansion of social attention to AI (e.g. acute labor displacement), and a less "technocratic" reaction. Will the first big federal AI bill feel more like the CARES Act or the CHIPS Act?

130

Chris Painter @chris.bsky.social · 23/12/2024

I think AI would benefit from more social contact with scientists in fields whose questions don't have intuitively verifiable answers. To assess model capability, I find myself often relying on happenstance anecdotes I hear from e.g. lab-bench researchers months after the fact.

140

Chris Painter @chris.bsky.social · 22/12/2024

I’m not sure that’s going to be a very meaningful distinction for the most advanced models, and I guess I’m specifically interested in what’s possible with both the best models-as-agents and models-as-tools

120

Chris Painter @chris.bsky.social · 22/12/2024

Will human-level AI be self-deploying/"productizing", or not? Will the "the product can explain to you how to use it and apply it" dynamic dramatically increase the adoption of AI relative to historical comparisons like AVs and steam engines?

140

Chris Painter @chris.bsky.social · 10/12/2024

Or man, idk, is it a "corollary"? Maybe it's just an example

010

Chris Painter @chris.bsky.social · 10/12/2024

A corollary to this: I think many policy initiatives would benefit from having more deeply engaged and informed opponents, and this is a neglected niche in many areas/topics. Detailed proposals having better (in the sense of more substantive) opponents is good for the world

241

Chris Painter @chris.bsky.social · 10/12/2024

I think the world could always benefit from more good-faith really in-depth critique of effortful technical/intellectual work. Many organizations that I collaborate with publish work hoping to have their ideas improved upon or attacked, but often surprisingly few people engage.

030

Chris Painter @chris.bsky.social · 10/12/2024

I’ve been wondering, has the (bad) reaction to this actually been that unusual?

010

Chris Painter @chris.bsky.social · 09/12/2024

Luigi Mangione's review of the Unabomber manifesto on Goodreads

151

Chris Painter @chris.bsky.social · 08/12/2024

Uber Eats is truly an embarrassment of riches. We are living in a golden age of delivered food.

010