DeepMind isn't doing safety engineering; they're doing standard AI. It doesn't matter if Elon Musk is interested in AI safety, if, after his deliberations, he invests in efforts to develop unsafe AI. Good intentions don't leak value into the consequences of your acts.
You are never going to catch up, and neither is anyone else.
-- Gian-Carlo Rota
Bob will accept that some phrase X is meaningful if there is a test that can be performed whose outcome value depends on truth value of X. If there is such a test, then we can construct a further test of asking someone who has performed the original test what the outcome of the test was. Since the people who set up tests are usually honest, this test would also be a test of X (provided the original test exists).
If I ask an honest peasant how long the emperor's nose is, but I also suspect no one has ever seen the emperor, how much do I learn from her statem...
Do you choose that rephrasing because you don't see how MIRI's work could be harmful or because there is nothing CFAR can do in that case?
Richard Jeffrey!
The man on the left is Hans Reichenbach.
No, I don't dislike that Brienne et al. ran the experiment. They can spend their time how they like, and quantitative self-help is admirable. But we didn't get to the quantitative part yet, so I'm very confused that this post was so well received. It reflects a problem more severe than community standards falling because individuals are unwilling to bear the cost of speaking out; individuals are actively encouraging low standards. Or that's how it seemed before people responded to me. Now my probability mass is mostly split between my values being weird or...
I made the post despite not having detailed quantitative information yet because people are curious. I made a post before promising the results of a very high VOI experiment, so people kept sending me messages along the lines of, "Ok, the month of the experiment is over! What happened?" and I didn't want them to lose interest or think the whole thing had been abandoned. I think this post was fairly well received because it was effective at reassuring people that the good thing they care about continues to exist and be good. Further, it's provided...
If adopting a weird sleep schedule has a high cost for the experimenter, that also offsets any potential payoff of adopting one on the experiment's basis. The experiment so far hasn't yielded any valuable results, because we already knew that a mild polyphasic schedule can be maintained (siestas), and that only running on naps is difficult (college students). Sleep deprivation is interesting and cognitive test results are fun to read; other than that novelty I don't see the VoI, because we already know with confidence what to expect from the test: slowed reactions and limited attention, with more extreme impairment for more deviant sleep schedules.
I upvoted because somebody on the Internet said they were going to do something and then actually did it.
I upvoted out of gratitude for doing an experiment that involves personal sacrifice and has a high potential payoff for all of us, and to suggest that I eagerly await the cognitive battery results.
For Snape, I was specifically thinking of the scene in Dumbledore's office where Harry reveals that he knows about the prophecy and Snape reacts without hesitation as though he hadn't heard of it. Snape was also a double agent during the war, and continues to maintain close relationships with Dumbledore and Lucius Malfoy. His actions do seem crude, awkward, uncontrolled or mostly defensive in other scenes such as in the bullying arc or his conversation with Quirrell in the forbidden forest in Chapter 77. But then, one can act with false impulsiveness too.
I suppose the characters are in a cold war and in the shadow of a hot war. That circumstance makes "offensive" deception in one's social presentation more useful.
Quirrell, Dumbledore, Snape, Harry, and (increasingly) Draco have something in common. They are all creepy. These characters are intentionally inauthentic - acting as though they posses the specific beliefs, preferences, and abilities that they want others to attribute to them.
I feel unusually strong revulsion about this kind of deception - more than toward someone hiding their faults to manage their appearance, much more than toward someone being tactful and withholding or biasing sensitive claims to avoid conflict.
When I try to unpack "creepy",...
Ha, thanks. Fixed.
Big tube in the air rests on pylons / support towers. Maybe goes along a highway. Vehicle inside the tube has batteries for running a compressor. It pumps air away from its front to reduce air resistance, pumps below for suspension and behind. High subsonic speed (~700 mi/hr, 1100 km/hr). Accelerated by occasional linear induction motors on the tube, like a maglev train. Vehicle estimated to cost millions, tube estimated to cost billions. Conventional rails cost tens of billions. That's all from the abstract, much more inside.
"Taking up a serious religion changes one's very practice of rationality by making doubt a disvalue." ~ Orthonormal
Another unsatisfying Nash equilibrium in traffic control I'd like to see analyzed from a modern decision theory perspective is Braess's Paradox.
I'm sorry to drop references without a summary, but this will have to do at the moment: "Lost thoughts: Implicit semantic interference impairs reflective access to currently active information"
Then he would have prepared for those >3 things failing to happen.
The path leading to disaster must be averted along every possible point of intervention.
~ Quirinus Xanatos Quirrell
Every time I hear "Rest in Peace" my mind corrects with "...except not resting or at peace". Does anyone have a secular, naturalistic world view analogue? Like "whom we should remember with honor", but catchy.
One of Eliezer's stories (http://lesswrong.com/lw/p1/initiation_ceremony/) uses the formula "Is dead but not forgotten." It's not bad even if I personally would prefer "gone but not forgotten".
Draco and Lucius, Snape, Bellatrix, Amelia Bones. Maybe the Weasley parents or Nicholas Flamel. I haven't given up on Minerva. Grindelwald is still alive and undemented.
Robin often displays unusual confusions. I think that stems from a reliance on his explicit memory over implicit memory. If he doesn't have a theory to account for why society fails to distinguish songs by whether their lyrics are fictional, as we do with literature, then he considers that a puzzle to solve, even if he's never wanted society to draw that category to aid him in selecting songs.
So when Robin asks, "Why do we appear to value X more than Y", he's not making any claim about how he feels about X and Y. He disregards his feelings and i...
Getting people to stop existing might not be the right thing to do, but there are many people who should not be created. All else equal, I feel people whose children would be at a high risk for horrible diseases like depression should avoid procreating until the state of genetic engineering or embryo selection is much advanced (in both reliability and generality of factors identified).
Well, not at all for the literal complexity of agents, because we don't estimate the complexity of our peers. Aristotle thought the heart was the seat of intelligence, Shannon thought AGI could be built in a year, everyone and their mother anthropomorphizes inanimate objects like smoke alarms and printers.
I suspect perceived character traits that engender distrust, the Dark Triad traits, make the trait-possessor seem complex not because their brain must be described in more bits absolutely, but conditionally given the brain of the character judge. That is...
No. Elsewhere he has said "I believe that consciousness is the way information feels when being processed", but in this talk he seems to make a little bit of a retreat. He describes a positive singularity with p-zombie AI/robots that have perception and appear conscious, but aren't "aware" of the world around them. He makes no clarification of how perception differs from awareness and doesn't mention introspection at all.
What? Rock climbing demonstrates depth? Circus skills are virtuous?
Which hobbies are especially shallow and narcissistic? Arts, crafts, gardening, cooking? Team sport, extreme sport, cycling, karate, yoga? Romance novels, short films, video games? Genealogy, collecting, puzzle solving? Card games, brewing, stage magic, lock picking? Sailing, camping, fishing, geocaching, trainspotting?
You are right that a cluster exists, and not everyone will be a con-langing, rocket building, capoeira fighter, but the attributes you're naming don't select for that group (or any group really).
An argument that halts in disagreement (or fails to halt in agreement) because the interlocutors are each waiting for another to provide a skillful assessment of their own inexpertly-referenced media sounds a lot like a software process deadlock condition in computer science. Maybe there's a more specific type of deadlock, livelock, resource starvation, ..., in the semantic neighborhood of your identified pattern.
Dropping references, while failing to disclaim your ability to evaluate the quality and relevance of topical media, could be called a violation ... (read more)