We have 3 of 58 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Results show that adaptive direction can emerge without being explicitly specified as a behavioral objective, and the same persistence that makes such adaptive agency useful can also allow misalignment, corrupted state and unintended behavior to persist across task boundaries.
A causal taxonomy separating prior commitment from retrospective report, model preference from realized output, false preference from sensitivity to the utility of misleading a recipient, and deceptive behavior from the provenance of the objective or strategy producing it is introduced.
A trust model is developed that places the authority to act outside the model, in code: a source's standing, not its content, decides which operation runs and whether it acts, and an unmodified model runs inside a deterministic pipeline.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
