Source type: official company news
Supports: Capability · defence applications
Source location: capabilities.0.applications.1
LawZero: Scientific hypothesis generation LawZero explains its disinterested predictor and explicitly limits the formal safety argument to stated assumptions rather than universal AI safety.
Supports: Capability · technicaldomainslugs
Source location: capabilities.0.technicalDomainSlugs.0
LawZero explains its disinterested predictor and explicitly limits the formal safety argument to stated assumptions rather than universal AI safety. Assessment for LawZero: mission-software-and-data
Supports: Capability · defence applications
Source location: capabilities.0.applications.0
LawZero: AI assurance research LawZero explains its disinterested predictor and explicitly limits the formal safety argument to stated assumptions rather than universal AI safety.
Supports: Capability · name
Source location: capabilities.0.name
LawZero: Scientist AI prediction and assurance research LawZero explains its disinterested predictor and explicitly limits the formal safety argument to stated assumptions rather than universal AI safety.
Supports: Capability · technical tags
Source location: capabilities.0.technicalTags.0
LawZero identifies LawZero: AI safety. LawZero explains its disinterested predictor and explicitly limits the formal safety argument to stated assumptions rather than universal AI safety.
Supports: Capability · core features
Source location: capabilities.0.features.0
LawZero: Disinterested probabilistic prediction LawZero explains its disinterested predictor and explicitly limits the formal safety argument to stated assumptions rather than universal AI safety.
Supports: Capability · summary
Source location: capabilities.0.summary
LawZero: Scientist AI is a research approach to models that generate explanatory hypotheses and probabilistic predictions without pursuing objectives of their own. LawZero proposes separating prediction from action and using the predictor to assess potentially harmful behavior by other systems. Its formal argument is conditional and addresses hidden goal formation in the predictor; experiments are proposed to test assumptions. Broader agent safety and practical assurance performance remain research questions.
Supports: Capability · core features
Source location: capabilities.0.features.1
LawZero: Separation of prediction from action LawZero explains its disinterested predictor and explicitly limits the formal safety argument to stated assumptions rather than universal AI safety.
Supports: Capability · capability type
Source location: capabilities.0.capabilityType
LawZero explains its disinterested predictor and explicitly limits the formal safety argument to stated assumptions rather than universal AI safety. Assessment for LawZero: AI safety research
Supports: Capability · technical tags
Source location: capabilities.0.technicalTags.1
LawZero: Probabilistic reasoning LawZero explains its disinterested predictor and explicitly limits the formal safety argument to stated assumptions rather than universal AI safety.
Supports: Capability · maturity
Source location: capabilities.0.maturity
LawZero: Research and engineering development supported by a published formal safety-case proposal; no attained TRL stated.
Supports: Capability · commercial availability
Source location: capabilities.0.commercialAvailability
LawZero: Research collaboration and emerging technical development; no general production-service availability established.
Supports: Capability · core features
Source location: capabilities.0.features.2
LawZero: Research on guardrails for other AI systems LawZero explains its disinterested predictor and explicitly limits the formal safety argument to stated assumptions rather than universal AI safety.
