InFeeo
Global
technology-news
New
Language
Profile channel

@Nikobar

No bio yet.

Since 06.06.2026

LawZero: Safety from Honesty in a Disinterested AI Predictor(doi.org)
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements. We argue that such a Predictor can honestly predict agents, actions, and their consequences without itself being an agent that selects outputs to achieve goals. This rests on data representation and on the training procedure. Epistemic contextualization of text distinguishes latent factual claims from communication acts, so expressions of goals are treated as evidence to be explained rather than drives the model adopts. With a posterior-seeking training objective, this is intended to drive the Predictor toward calibrated, cautious predictions. Training proceeds so downstream effects of deploying a prediction never serve as a reward signal; any agency the system needs is supplied by explicit scaffolding constrained by guardrails. We prove that, under assumptions on the training dynamics and on the argued sparsity of dangerous Predictors, the probability that training produces a Predictor whose guarded deployment carries residual harm above a specified threshold is small: a dangerous Predictor would have to underestimate harm in a coordinated way across many queries while such coordinated patterns are rare under the initialization distribution and receive no direct training signal. Safety and accuracy are jointly supported in this framework, since the constraints that secure accuracy are the same ones that make coordinated deception costly. These guarantees against misalignment and agency arising from within the Predictor itself do not preclude the use of the Predictor as part of an agentic system.
AMilliSol(sprit.org)
Die Domain www.pumpfun.com ist zurzeit geparkt. Sie möchten eine eigene Website unter www.pumpfun.com online stellen? Sprit.org stellt Ihnen für jeden Bedarf Hostinglösungen zur Verfügung um Ihren eigenen Internetauftritt zu realisieren. Buchen Sie unsere Hostingpakete ab € 1,90 pro Monat und starten Sie mit Ihrem eigenen Internetauftritt durch. Betreten Sie einfach mittels Ihres Benutzernamens und Passwortes Ihren persönlichen Kundenbereich unter www.sprit.org Sprit.org Domain- und Webhosting Weyringergasse 13, 1040 Wien www.sprit.org