A man sits in a jail cell, condemned to die. In the morning he will face a firing squad; this is his last night on earth. What should he do?
Should he try to forget his impending execution, pretending to himself that a pardon must certainly be on the way, that he surely must soon be reprieved? Should he rattle on the bars of his cell all night, helplessly begging and pleading for mercy? Should he tirelessly chip at the concrete walls with the battered remnants of a spoon, despite the impossibility a successful escape?
None of those sound all that great, do they? Each is pathetic, in its own way. Perhaps the third most of all: going through the motions of an escape attempt with no actual hope of success is not “actually trying”. It’s just as much of a refusal to face reality as the first is, or more so.
Perhaps he should compose himself, try to get a good night’s sleep, then in the morning wake up and walk calmly to his execution with his head held high. I must admit, I don’t particularly like that option either, but it is better than the first three. There is something brave and noble in it that there isn’t in the others, though the man ends up just as dead.
When I lived in Russia, I would occasionally go to a protest rally and get detained. One day I was sitting in a police station, waiting for my 3 hours to pass, and no one was paying attention to me. So I decided to try, what is going to happen if I get up and walk out? I walked out and no one stopped me. I tried that 4 times and it worked 3 times. No one bothers to guard detained protesters because no one bothers to try and escape.
I don’t know why everyone suddenly decided that alignment problem is “impossible”, Eliezer just said that it’s hard and he wants more help, preferably soon. It was a call for action, not a call to give up.
It’s possible that in convincing everyone it wasn’t trivial, he overshot and convinced many that it was impossible. Or maybe it actually is impossible. Certainly that’s how it feels to me. Additionally, it’s unclear HOW most of us can help or know if we’re helping—there’s no analog to “try walking out” that I can see.
By thinking about it yourself or donating to some org. I agree that it’s hard to know if you’re helping, and I don’t advocate donating if an org looks 99% likely to be scammy or useless.
A man sits in a jail cell, condemned to die. In the morning he will face a firing squad; this is his last night on earth. What should he do?
Should he try to forget his impending execution, pretending to himself that a pardon must certainly be on the way, that he surely must soon be reprieved? Should he rattle on the bars of his cell all night, helplessly begging and pleading for mercy? Should he tirelessly chip at the concrete walls with the battered remnants of a spoon, despite the impossibility a successful escape?
None of those sound all that great, do they? Each is pathetic, in its own way. Perhaps the third most of all: going through the motions of an escape attempt with no actual hope of success is not “actually trying”. It’s just as much of a refusal to face reality as the first is, or more so.
Perhaps he should compose himself, try to get a good night’s sleep, then in the morning wake up and walk calmly to his execution with his head held high. I must admit, I don’t particularly like that option either, but it is better than the first three. There is something brave and noble in it that there isn’t in the others, though the man ends up just as dead.
When I lived in Russia, I would occasionally go to a protest rally and get detained. One day I was sitting in a police station, waiting for my 3 hours to pass, and no one was paying attention to me. So I decided to try, what is going to happen if I get up and walk out? I walked out and no one stopped me. I tried that 4 times and it worked 3 times. No one bothers to guard detained protesters because no one bothers to try and escape.
I don’t know why everyone suddenly decided that alignment problem is “impossible”, Eliezer just said that it’s hard and he wants more help, preferably soon. It was a call for action, not a call to give up.
It’s possible that in convincing everyone it wasn’t trivial, he overshot and convinced many that it was impossible. Or maybe it actually is impossible. Certainly that’s how it feels to me. Additionally, it’s unclear HOW most of us can help or know if we’re helping—there’s no analog to “try walking out” that I can see.
By thinking about it yourself or donating to some org. I agree that it’s hard to know if you’re helping, and I don’t advocate donating if an org looks 99% likely to be scammy or useless.