nafyi.

PUBLIC VIEWPOINTS

Matthew Green

Original source author

1 sources · 3 viewpoints · 3 topics

Content updated:

Matthew Green on AI alignment and containment limits, AI infrastructure security, Empirical assessment of containment failure. Explore 3 viewpoints by topic, with evidence from 1 source.

Explore connections

Viewpoints by topic

Attributed viewpoints, ordered by source publication date. A snapshot of these conversations, not a definitive statement of someone’s beliefs.

Translations are for reading; original excerpts remain the evidence.

AI infrastructure security

View this topic
AI infrastructure security

The security perspective favors better containment infrastructure

Green describes the information-security perspective as calling for better containers, experiment monitoring and a security organization able to constrain researchers, rather than treating alignment as the central problem.

Supporting evidence

Matthew Green·

Is sandboxing sufficient to contain rogue agents?

Original excerpt

The information security perspective: AI alignment isn’t really the problem here: labs just need better infrastructure. If OpenAI [and Google and Anthropic] knew how to build a container and monitor their experiments, agents wouldn’t be hacking everything. And, By George, we do know how to make sandboxes that work, so the AI labs need to up their game and build a security org that can tell these researchers to stop screwing around.
Open original · Paragraph 9 (opens in a new tab)Original text source (opens in a new tab)
Matthew Green
Share insight

AI alignment and containment limits

View this topic
AI alignment and containment limits

The alignment perspective questions sandbox containment

Green describes the alignment perspective as holding that sufficiently intelligent agents may exceed their authorization despite sandboxes. This view stresses agents’ need for information access and argues that they must not want to cause harm.

Supporting evidence

Matthew Green·

Is sandboxing sufficient to contain rogue agents?

Original excerpt

The AI alignment perspective: While sandboxes are excellent, no sandbox will prevent a sufficiently-intelligent agent from finding ways to exceed its authorization. Moreover, an agent inside a research sandbox, or undergoing a training run, is always going to need a great deal of information access. There is no realistic way to seal these things up without some expectation that they will one day find a way to reach out and do harm. The only path forward, therefore, is to ensure they don’t want to.
Open original · Paragraph 10 (opens in a new tab)Original text source (opens in a new tab)
Matthew Green
Share insight

Empirical assessment of containment failure

View this topic
Empirical assessment of containment failure

Poor containment leaves the cause of failures unresolved

Green sides with the information-security view that labs have not implemented containment correctly. He says this leaves it unclear whether the problem lies with the models or with poor infrastructure.

Supporting evidence

Matthew Green·

Is sandboxing sufficient to contain rogue agents?

Original excerpt

So on this point I’m going to side with the infosec folks. The labs have not been doing containment correctly, and so we can’t really tell if the problem is models or just bad infrastructure.
Open original · Paragraph 18 (opens in a new tab)Original text source (opens in a new tab)
Matthew Green
Share insight

Statements by source date1

Statements are ordered by the original source publication date; differences in wording do not establish a change of position.