[extropy-chat] The athymhormic AI

[Rafal Smigrodzki]

Last week I commented here on the low likelihood of an AI designed as a pure
epistemic engine (like a cortex without much else) turning against its owners,
which I derived from the presence of complex circuitry in humans devoted to
producing motivation and a goal system.

Now I found more about actual neurological conditions where this circuitry is
damaged, resulting in reduced volition with preserved mentation. Athymhormia,
as one of the forms of this disorder is called, is caused by interruption of
the connections between frontopolar cortex and the caudate, the subcortical
circuit implicated in sifting through motor behaviors to find the ones likely
to achieve goals. An athymhormic person loses motivation even to eat, despite
still being able to feel hunger in an intellectual, detached manner. At the
same time he has essentially normal intelligence if prodded verbally, thanks to
preservation of the cortex itself, and connections from other cortical areas
circumventing the basal ganglia.

I would expect that the first useful general AI will be athymhormic, at least
mildly so, rather than Friendly. What do you think, Eliezer?

Rafal

See the ref:

Athymhormia and disorders of motivation in Basal Ganglia disease.

Habib M.

Pediatric Neurology, Hopital La Timone, 13385 Marseille Cedex 5, France.
rnp at univ-aix.fr

The author proposes a general model of human motivation as a separate function
at the interface between emotion and action, which can be ascribed to
subcortical circuits that are mainly centered on a subset of the basal ganglia
and on their limbic connections. It is argued that the long-standing historical
understatement of the notion of motivation in neurology is not only due to the
complexity of the issue, which has proven hard to disentangle from other
domains of dysfunction, but also to the persistence of some misleading
conceptual orientations in the way neurologists have considered the brain
mechanisms of goal-directed action, torn between a nonspecific "activation"
view and an exclusively cognitive conception of motivation. How combining early
clinical intuitions of some psychiatrists, careful clinical observations of
neurological patients, and data derived from experimental studies in animals
provide the basis for a coherent model of human motivation and its specific
impairment in clinical neurology is explained. Clinical implications that can
be drawn from such a model for some neuropsychiatric conditions are proposed.