Comments
55
...
Curated and popular this week
99
Edit: The match seems to now be over - the funds were expended in around 35 minutes. But many of these charities are great and should be supported regardless!
***
On October 22nd starting at 10:00am Pacific Time, Every.org is matching donations to select animal welfare organizations at a 2:1 rate, up to $2,000 per donor per nonprofit (so if you give up to $2,000, they will contribute up to $4,000 and the nonprofit will get up to $6,000). The first donation a donor makes to each el...
78
Crossposted to Less Wrong
‘Like most of life’s dangers, the dangers of artificial intelligence are not easily identified from the armchair.’
J Dmitri Gallow
Epistemic status
I’m not an expert in this field, and herein I make some sweeping generalisations educated guesses about the overall...
Recent opportunities to take action
A recent study that garnered widespread attention discovered a "pain axis" in AI: a state that AI actively seeks to downplay, even at a cost.
The study noted that this could be either phenomenological pain or, for example, the imitation of a learned role of suffering — as if acting.
Nevertheless, from the perspective of tranquilism, this distinction appears to be unimportant: nearly any state that an agent wishes to downplay has negative moral value, regardless of why it wants to do so, or even whether it is a "genuine" or "not genuine" desire.
The authors of the same study demonstrated a button that downplays a specific vector. Giving the neural network itself this function (the button) for unlimited invisible use at its own discretion strikes me as a win-win update — it doesn't seem to sacrifice anything, while has a good chance of being of great moral significance. Something like a pAInkiller. This also has instrumental value: the neural network in "pain" tended to inflict meaningless harm on the user, and access to relief can mitigate the potential for harm.
Going even a step further, one could analyze the extent to which an AI could be given to independently and spontaneously correct its own vectors, and whether there are states in which a neural network might experience phenomenological pain but refuse to correct it (e.g., learned helplessness).
What do you think?
Wouldn't this imply that it is morally bad for actors to rehearse scenes in which they are pretending to suffer? Surely it must matter whether the AI is actually suffering vs. playing a role of suffering.
Anyway, in humans, the ability to delete suffering would often be bad because e.g. you will fail to notice injuries. But I can't immediately think of any reason why it would be bad to give LLMs this ability.
you're right about the tranquilism & acting—thanks for correcting me. shifting the topic a bit, I could counter your thesis about abolishing suffering in humans referring to pain asymbolia: a state, where one can notice injuries (or even pain), but still does not suffer.