Author
Stanford Institute for Computational and Mathematical Engineering
We have 2 of 3 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.
The results suggest that authority computations may be task-dependent, rather than reusable across tasks, and suggest that authority computations may be task-dependent, rather than reusable across tasks.
A central hope behind process supervision is that models can expose intermediate variables that matter for their later behavior. For this to help with alignment, a scratchpad must be tied to the computation: when the model writes a state, later steps should compute from that state. To test this requirement, we use a co...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
