I'm delighted that Anthropic has formally committed to our responsible scaling policy. We're also sharing more detail about the Long-Term Benefit Trust, which is our attempt to fine-tune our corporate governance to address the unique challenges and long-term opportunities of transformative AI.


Today, we’re publishing our Responsible Scaling Policy (RSP) – a series of technical and organizational protocols that we’re adopting to help us manage the risks of developing increasingly capable AI systems.

As AI models become more capable, we believe that they will create major economic and social value, but will also present increasingly severe risks. Our RSP focuses on catastrophic risks – those where an AI model directly causes large scale devastation. Such risks can come from deliberate misuse of models (for example use by terrorists or state actors to create bioweapons) or from models that cause destruction by acting autonomously in ways contrary to the intent of their designers.

image overview of AI Safety Levels

Our RSP defines a framework called AI Safety Levels (ASL) for addressing catastrophic risks, modeled loosely after the US government’s biosafety level (BSL) standards for handling of dangerous biological materials. The basic idea is to require safety, security, and operational standards appropriate to a model’s potential for catastrophic risk, with higher ASL levels requiring increasingly strict demonstrations of safety.

A very abbreviated summary of the ASL system is as follows:

  • ASL-1 refers to systems which pose no meaningful catastrophic risk, for example a 2018 LLM or an AI system that only plays chess.
  • ASL-2 refers to systems that show early signs of dangerous capabilities – for example ability to give instructions on how to build bioweapons – but where the information is not yet useful due to insufficient reliability or not providing information that e.g. a search engine couldn’t. Current LLMs, including Claude, appear to be ASL-2.
  • ASL-3 refers to systems that substantially increase the risk of catastrophic misuse compared to non-AI baselines (e.g. search engines or textbooks) OR that show low-level autonomous capabilities.
  • ASL-4 and higher (ASL-5+) is not yet defined as it is too far from present systems, but will likely involve qualitative escalations in catastrophic misuse potential and autonomy.

The definition, criteria, and safety measures for each ASL level are described in detail in the main document, but at a high level, ASL-2 measures represent our current safety and security standards and overlap significantly with our recent White House commitments. ASL-3 measures include stricter standards that will require intense research and engineering effort to comply with in time, such as unusually strong security requirements and a commitment not to deploy ASL-3 models if they show any meaningful catastrophic misuse risk under adversarial testing by world-class red-teamers (this is in contrast to merely a commitment to perform red-teaming). Our ASL-4 measures aren’t yet written (our commitment is to write them before we reach ASL-3), but may require methods of assurance that are unsolved research problems today, such as using interpretability methods to demonstrate mechanistically that a model is unlikely to engage in certain catastrophic behaviors.

We have designed the ASL system to strike a balance between effectively targeting catastrophic risk and incentivising beneficial applications and safety progress. On the one hand, the ASL system implicitly requires us to temporarily pause training of more powerful models if our AI scaling outstrips our ability to comply with the necessary safety procedures. But it does so in a way that directly incentivizes us to solve the necessary safety issues as a way to unlock further scaling, and allows us to use the most powerful models from the previous ASL level as a tool for developing safety features for the next level.[1] If adopted as a standard across frontier labs, we hope this might create a “race to the top” dynamic where competitive incentives are directly channeled into solving safety problems.

From a business perspective, we want to be clear that our RSP will not alter current uses of Claude or disrupt availability of our products. Rather, it should be seen as analogous to the pre-market testing and safety feature design conducted in the automotive or aviation industry, where the goal is to rigorously demonstrate the safety of a product before it is released onto the market, which ultimately benefits customers.

Anthropic’s RSP has been formally approved by its board and changes must be approved by the board following consultations with the Long Term Benefit Trust. In the full document we describe a number of procedural safeguards to ensure the integrity of the evaluation process.

However, we want to emphasize that these commitments are our current best guess, and an early iteration that we will build on. The fast pace and many uncertainties of AI as a field imply that, unlike the relatively stable BSL system, rapid iteration and course correction will almost certainly be necessary.

The full document can be read here. We hope that it provides useful inspiration to policymakers, third party nonprofit organizations, and other companies facing similar deployment decisions.

We thank ARC Evals for their key insights and expertise supporting the development of our RSP commitments, particularly regarding evaluations for autonomous capabilities. We found their expertise in AI risk assessment to be instrumental as we designed our evaluation procedures. We also recognize ARC Evals' leadership in originating and spearheading the development of their broader ARC Responsible Scaling Policy framework, which inspired our approach.. [italics in original]


I'm also including a short excerpt from the Long-Term Benefit Trust post, which I suggest reading in full. You may also wish to (re-)read Anthropic's core views on AI safety as background.

The Anthropic Long-Term Benefit Trust (LTBT, or Trust) is an independent body comprising five Trustees with backgrounds and expertise in AI safety, national security, public policy, and social enterprise. The Trust’s arrangements are designed to insulate the Trustees from financial interest in Anthropic and to grant them sufficient independence to balance the interests of the public alongside the interests of Anthropic’s stockholders. ... the Trust will elect a majority of the board within 4 years. ...

The initial Trustees are:

The Anthropic board chose these initial Trustees after a year-long search and interview process to surface individuals who exhibit thoughtfulness, strong character, and a deep understanding of the risks, benefits, and trajectory of AI and its impacts on society. Trustees serve one-year terms and future Trustees will be elected by a vote of the Trustees. We are honored that this founding group of Trustees chose to accept their places on the Trust, and we believe they will provide invaluable insight and judgment.


  1. As a general matter, Anthropic has consistently found that working with frontier AI models is an essential ingredient in developing new methods to mitigate the risk of AI. ↩︎

New Comment
5 comments, sorted by Click to highlight new comments since: Today at 5:07 PM

As a general matter, Anthropic has consistently found that working with frontier AI models is an essential ingredient in developing new methods to mitigate the risk of AI.

What are some examples of work that is most largeness-loaded and most risk-preventing? My understanding is that interpretability work doesn't need large models (though I don't know about things like influence functions). I imagine constitutional AI does. Is that the central example or there are other pieces that are further in this direction?

I am surprised to see the Open Philanthropy network taking all of the powerful roles here.

The initial Trustees are:

In case it's not apparent:

  • Jason Matheny started an org with over $40M of OpenPhil funding (link to the biggest grant)
  • Kanika Bahl runs Evidence Action, an org that OpenPhil has donated over $100M to over the past 7 years
  • Neil Buddy Shah was the Managing Director at GiveWell for 2.5 years. GiveWell is the organization that OpenPhil grew out of between 2011 and 2014 and continued to maintain close ties with over the decade (e.g. sharing an office for ~5 more years, deferring substantially to GiveWell recommendations for somewhere in the neighborhood of $500M of Global Health grants, etc).
  • Paul Christiano is technically the least institutionally connected to OpenPhil. Most commenters here are quite aware of Paul's relationship to Open Philanthropy, but to state some obvious legible things for those who are not: Paul is married to Ajeya Cotra, who leads the AI funding at OpenPhil, has been a technical advisor to OpenPhil in some capacity since 2012 (see him mentioned in the following pages: 1, 2, 3, 4, 5, 6), and Holden Karnofsky has collaborated with  / advised Paul's organization ARC (collaboration mentioned here and shown as an advisor here).
  • Zach Robinson worked at OpenPhil for 3 years, over half of which was spent as Chief of Staff.

And, as a reminder for those who've forgotten, Holden Karnofsky's wife Daniela Amodei is President of Anthropic (and so Holden is the brother-in-law of Dario Amodei).

Trustees serve one-year terms and future Trustees will be elected by a vote of the Trustees

One year is shockingly short, why such fast turnaround?

And great post I'm excited to see responsible scaling policies becoming a thing!

One year is actually the typical term length for board-style positions, but because members can be re-elected their tenure is often much longer. In this specific case of course it's now up to the trustees!

The model shows early signs of autonomous self-replication ability, as defined by 50% aggregate success rate on the tasks listed in [Appendix on Autonomy Evaluations]

Would you be willing to rephrase this as something like

The model shows early signs of autonomous self-replication ability. Autonomous self-replication ability is defined as 50% aggregate success rate on the capabilities for which we list evaluations in [Appendix on Autonomy Evaluations]

?

The hope here is to avoid something like "well this system doesn't have autonomous self-replication ability/isn't ASL-3, because Anthropic's evals failed to elicit the behaviour. That definitionally means it's not ASL-3", and get a bit more map-territory distinction in.