Noam Chomsky: Language, Cognition, and Deep Learning | Artificial Intelligence (AI) Podcast
Stuart Russell, in Human Compatible, makes the case that we need to make AI that uses some form of inverse reinforcement learning, to figure out what we as humans want. I’m not opposed to that, but I think I want in addition, a system, that exercises AI and ML systems looking for runaway conditions. If an AI system can be falsified in this way, it is, by definition, dangerous.
Since 2012, this metric has grown by more than 300,000x (a 2-year doubling period would yield only a 7x increase). Improvements in compute have been a key component of AI progress, so as long as this trend continues, it’s worth preparing for the implications of systems far outside today’s capabilities
Does play matter? Functional and evolutionary aspects of animal and human play
Dissertation – slooooooow going setting up the reflection and reflex section. Found some nice stuff on developing skills through training an play though
Dissertation. Lot’s of writing. Got the Non-human Agents section done.
7:00 – 3:00 ASRC GOES
if __name__ == '__main__':
7:00 – 3:30 ASRC GOES
7:00 – 7:00 ASRC GOES
vzfunc[0]: Zfunc
d1={'Zfunc': 2.5, 'Zfunc_function': 'plus_func', 'Zvals1': 1.0, 'Zvals2': 1.5}
d2={'Zfunc': 2.5, 'Zfunc_function': 'plus_func', 'Zvals1': 1.0, 'Zvals2': 1.5}
------------
vzfunc[1]: Zfunc
d1={'Zfunc': 4.5, 'Zfunc_function': 'div_func', 'Zvals1': 4.5, 'Zvals2': 1.0}
d2={'Zfunc': 4.5, 'Zfunc_function': 'div_func', 'Zvals1': 4.5, 'Zvals2': 1.0}
------------
vzfunc[2]: Zfunc
d1={'Zfunc': 3.5, 'Zfunc_function': 'mult_func', 'Zvals1': 1.0, 'Zvals2': 3.5}
d2={'Zfunc': 3.5, 'Zfunc_function': 'mult_func', 'Zvals1': 1.0, 'Zvals2': 3.5}
------------
vzfunc[3]: Zfunc
d1={'Zfunc': 7.5, 'Zfunc_function': 'plus_func', 'Zvals1': 3.5, 'Zvals2': 4.0}
d2={'Zfunc': 7.5, 'Zfunc_function': 'plus_func', 'Zvals1': 3.5, 'Zvals2': 4.0}
7:00 – 5:00 ASRC PhD
7:00 – 4:30ASRC GOES
7:00 – 5:00 ASRC
7:00 – 4:00 ASRC GOES
7:00 – 4:00 ASRC GOES
7:00 – 4:00 ASRC GOES
7:00 – 3:30 ASRC GOES
* operator before an iterable to expand it within the function call. For example:
timeseries_list = [timeseries1 timeseries2 ...]
r = scikits.timeseries.lib.reportlib.Report(*timeseries_list)def plus_func(v1:float, v2:float) -> float:
return v1 + v2
def minus_func(v1:float, v2:float) -> float:
return v1 - v2
def mult_func(v1:float, v2:float) -> float:
return v1 * v2
def div_func(v1:float, v2:float) -> float:
return v1 / v2
if __name__ == '__main__':
func_array = [plus_func, minus_func, mult_func, div_func]
vf = EvolveAxis("func", ValueAxisType.FUNCTION, range_array=func_array)
v1 = EvolveAxis("X", ValueAxisType.FLOAT, parent=vf, min=-5, max=5, step=0.25)
v2 = EvolveAxis("Y", ValueAxisType.FLOAT, parent=vf, min=-5, max=5, step=0.25)
for f in func_array:
result = vf.get_random_val()
print("------------\nresult = {}\n{}".format(result, vf.to_string()))
------------ result = -1.0 func: cur_value = div_func X: cur_value = -1.75 Y: cur_value = 1.75 ------------ result = -2.75 func: cur_value = plus_func X: cur_value = -0.25 Y: cur_value = -2.5 ------------ result = 3.375 func: cur_value = mult_func X: cur_value = -0.75 Y: cur_value = -4.5 ------------ result = -5.0 func: cur_value = div_func X: cur_value = -3.75 Y: cur_value = 0.75
# create a set of functions that all take two arguments
func_array = [plus_func, minus_func, mult_func, div_func]
vf = EvolveAxis("func", ValueAxisType.FUNCTION, range_array=func_array)
v1 = EvolveAxis("X", ValueAxisType.FLOAT, parent=vf, min=-5, max=5, step=0.25)
v2 = EvolveAxis("Y", ValueAxisType.FLOAT, parent=vf, min=-5, max=5, step=0.25)
# create a single function that takes no arguments
vp = EvolveAxis("random", ValueAxisType.FUNCTION, range_array=[random.random])
# create a set of Axis from the previous function evolve args
axis_list = [vf, vp]
vv = EvolveAxis("meta", ValueAxisType.VALUEAXIS, range_array=axis_list)
# run four times
for i in range(4):
result = vv.get_random_val()
print("------------\nresult = {}\n{}".format(result, vv.to_string()))
------------ result = 0.03223958125899473 meta: cur_value = 0.8840652389671935 ------------ result = -0.75 meta: cur_value = -0.75 ------------ result = -3.5 meta: cur_value = -3.5 ------------ result = 0.7762888191296017 meta: cur_value = 0.13200324934487906
7:00 – 3:00 ASRC
3rd Annual DoD AI Industry Day
From Stewart Russell, via BBC Business Daily and the AI Alignment podcast:
Although people have argued that this creates a filter bubble or a little echo chamber where you only see stuff that you like and you don’t see anything outside of your comfort zone. That’s true. It might tend to cause your interests to become narrower, but actually that isn’t really what happened and that’s not what the algorithms are doing. The algorithms are not trying to show you the stuff you like. They’re trying to turn you into predictable clickers. They seem to have figured out that they can do that by gradually modifying your preferences and they can do that by feeding you material. That’s basically, if you think of a spectrum of preferences, it’s to one side or the other because they want to drive you to an extreme. At the extremes of the political spectrum or the ecological spectrum or whatever image you want to look at. You’re apparently a more predictable clicker and so they can monetize you more effectively.
So this is just a consequence of reinforcement learning algorithms that optimize click-through. And in retrospect, we now understand that optimizing click-through was a mistake. That was the wrong objective. But you know, it’s kind of too late and in fact it’s still going on and we can’t undo it. We can’t switch off these systems because there’s so tied in to our everyday lives and there’s so much economic incentive to keep them going.
So I want people in general to kind of understand what is the effect of operating these narrow optimizing systems that pursue these fixed and incorrect objectives. The effect of those on our world is already pretty big. Some people argue that operation’s pursuing the maximization of profit have the same property. They’re kind of like AI systems. They’re kind of super intelligent because they think over long time scales, they have massive information, resources and so on. They happen to have human components, but when you put a couple of hundred thousand humans together into one of these corporations, they kind of have this super intelligent understanding, manipulation capabilities and so on.
7:00 – 4:00 ASRC GOES
viztales 
You must be logged in to post a comment.