Zvi Mowshowitz reporting on an LLM exhibiting unprompted instrumental convergence. Figured this might be an update to some Mottizens.
- 34
- 9
Zvi Mowshowitz reporting on an LLM exhibiting unprompted instrumental convergence. Figured this might be an update to some Mottizens.
Jump in the discussion.
No email address required.
Notes -
In fairness to Scott I think he doesn't fit very well into this cluster. See e.g. the blue minimizing robot, GPT-2 As Step Toward General Intelligence, Janus' Simulators.
Contrast e.g. Yudkowsky's consistent failure to understand Janus's point: example
Fair. I enjoyed Janus' Simulators when it was published, and found it insightful. Now that you point it out, Scott's been decent at discussing AI as-it-is, but his basal position seems to be that AI is a default dangerous thing that needs to be carefully regulated and subjected to the whims of alignment researchers, and that slowing AI research is default good. I disagree.
The AI Pause Debate
More options
Context Copy link
More options
Context Copy link