I seem to remember reading that the most promising near term methods of fine resolution brain imaging only work for the outer few mms/cms of the brain. So if “human alignment” lives deeper than that, and those methods are successful, they may not return much alignment benefit.
Non-invasive ultrasound + contrast (e.g. microbubbles) can reconstruct vasculature throughout the cranium. Merge is also working on tooling to increase the fidelity of ultrasound-based methods (see Mikhail Shapiro’s past research (cofounder of Merge) on e.g. gene therapies for acoustic phosphorescence) that would potentially provide single-neuron level resolution throughout the brain as well.
(There are also some other modalities people are exploring, but these are just the ones I’ve heard the most about that can image deeply)
I seem to remember reading that the most promising near term methods of fine resolution brain imaging only work for the outer few mms/cms of the brain. So if “human alignment” lives deeper than that, and those methods are successful, they may not return much alignment benefit.
Non-invasive ultrasound + contrast (e.g. microbubbles) can reconstruct vasculature throughout the cranium. Merge is also working on tooling to increase the fidelity of ultrasound-based methods (see Mikhail Shapiro’s past research (cofounder of Merge) on e.g. gene therapies for acoustic phosphorescence) that would potentially provide single-neuron level resolution throughout the brain as well.
(There are also some other modalities people are exploring, but these are just the ones I’ve heard the most about that can image deeply)