We could say that everything is conscious. That has the same meaning as nothing is conscious. But all we are doing is avoiding defining something that is really hard to define. Likewise with free will.
We will know we have properly modeled human minds in AGI if it claims to be conscious and have free will but is unable to tell you what that means. You can train it as follows: Positive reinforcement of perception trains belief in quality. Positive reinforcement of episodic memory recall trains belief in consciousness. Positive reinforcement of actions trains belief in free will. These are the things that make life better than death, which is good for reproductive fitness. On Wed, Sep 12, 2018, 9:21 AM John Rose <[email protected]> wrote: > > -----Original Message----- > > From: Matt Mahoney via AGI <[email protected]> > > > > I don't believe that my thermostat is conscious. Or let me taboo words > like > > "believe" and 'conscious". I assign a low probability to the possibility > that my > > thermostat has a homunculus or an immortal soul or a little person > inside it > > that feels hot or cold. I assign a low probability that human brains > have these > > either. When we look inside, all we see are neurons. > > The thermostat in a tiny binary way I would say is conscious. And I > speculate has a tiny bit of free will. > > It's hard to imagine but there are situations where the thermostat would > choose to save itself verses getting destroyed. How? Causal feedback into > its own negentropic complexity. It has a slight preference to exist. This > probably could be calculated... > > Note: I'm more thinking about thermostats that control heat and cold, > furnace and AC. Not sure about AC-only thermostats in warm areas 😊 > > > > > Your argument that I am conscious is to poke me in the eye and ask > whether I > > felt pain or just neural signals. My reaction to pain must either be > real or it > > must be involuntary and I lack the free will to ignore it. Well guess > what. Free > > will is an illusion too. If you don't believe me, then define it. > Something you > > can apply as a test to humans, thermostats, dogs, AI, etc. I'll wait... > > > > Part of free will is choosing to be responsible for your actions. Meaning? > Our actions are a discourse with the environment and other agents (aka. > people, animals, etc..) In conscious existence there are choices since we > believe other agents might be similarly conscious like ourselves even > though they could be zombies we err on the positive side. For example my > neighbor might actually feel pain so I don't maim him and take all his > consciousness enhancing feel-good things including food, money, women, > drugs 😊 > > I don't know if this answers your questions but perhaps is in the > direction of... > > John > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T9c94dabb0436859d-M2bfd453d99bc0c114e424986 Delivery options: https://agi.topicbox.com/groups/agi/subscription
