nafyi.

OPINIONS EXPRIMÉES EN PUBLIC

Matthew Green

Original source author

1 sources · 3 points de vue · 3 sujets

Contenu mis à jour:

Matthew Green sur AI alignment and containment limits, AI infrastructure security, Empirical assessment of containment failure. Explorez 3 points de vue par thème, avec des éléments tirés de 1 source.

Explorer les liens

Points de vue par sujet

Points de vue attribués, classés par date de publication de la source. Un aperçu de ces échanges, sans prétendre définir toutes les convictions de la personne.

Les traductions sont destinées à la lecture ; les extraits originaux restent la source evidence.

AI infrastructure security

Voir ce sujet
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.

Éléments favorables

Matthew Green·

Is sandboxing sufficient to contain rogue agents?

Extrait original

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.
Ouvrir l’original · Paragraphe 9 (s’ouvre dans un nouvel onglet)Source du texte original (s’ouvre dans un nouvel onglet)
Matthew Green
Partager un aperçu

AI alignment and containment limits

Voir ce sujet
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.

Éléments favorables

Matthew Green·

Is sandboxing sufficient to contain rogue agents?

Extrait original

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.
Ouvrir l’original · Paragraphe 10 (s’ouvre dans un nouvel onglet)Source du texte original (s’ouvre dans un nouvel onglet)
Matthew Green
Partager un aperçu

Empirical assessment of containment failure

Voir ce sujet
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.

Éléments favorables

Matthew Green·

Is sandboxing sufficient to contain rogue agents?

Extrait original

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.
Ouvrir l’original · Paragraphe 18 (s’ouvre dans un nouvel onglet)Source du texte original (s’ouvre dans un nouvel onglet)
Matthew Green
Partager un aperçu

Propos par date de source1

Les propos sont classés par date de publication de la source originale ; une différence de formulation ne prouve pas un changement de position.