SkepticalOne

Crabs have evolved to walk sideways in order to avoid running into Lobsters.

Though both possess the ability to make a nice salad.

Completely unrelated - I wonder if the seafood place down the road will be busy this evening...

Debby wrote:

Jesus is the real evidence of an after life. His resurrection was witnessed by thousands and recorded in the Bible for all times.

His claimed resurrection was said to have been witnessed by hundreds. Claims are not evidence.

RemyBrown wrote:

The United States should annex 100% of all of Canada without violence, as Canadian National Identity is futile, and therefore irrelevant.

I suspect Canada might disagree.

Hmmm, one month. ...just because.

Bud Lite and Nike valuation now, compared to even just two years ago, is evidence that woke [either 1 or 2] is DOA.

Budweiser has a higher valuation now than 3 years ago (when the woke happened) and Nike has plenty of non-woke challenges to explain their devaluation.

"Nike's challenges reflect a broader set of pressures facing the retail and consumer goods sector. Rising costs, changing consumer habits, inventory missteps and intensifying competition from brands like On and Hoka have all played a role. Meanwhile, China — once a crucial engine of growth — has become another major headache for the company, with Greater China revenue dropping 12% (5) in the most recent quarter." [Link]

These are not great exemplars of 'go woke, go broke'.

This is probably the single most relevant objection to OP. If the soul doesnt exist, then there can be no afterlife.

His breathing causes outrage to some...

Its not a moral failing on his part if his reasonable participation (and existence) upsets someone. Call it what it is: someone being irrationally offended by another person doing normal things.

Ragebaiting isnt 'I did my duty and people got upset about it'. Ragebaiting is intentionally trying to cause outrage. Mamdani did the former, not the latter.

The mayor goes to city events in his capacity as mayor, not because he is trying to trigger bigots....thats just a bonus. 😉

I'm just very skeptical of anti-doom arguments along the lines of "the AI won't be smart enough to do X"

To be clear, this is not my view. ASI will be able to do amazing things, but there is no level of intelligence that can overcome some hurdles. For instance, intelligence does not solve for chaotic systems...like security infrastructure. If information does not exist until the problem is encountered, then it is too late to utilize processing power to avoid the problem.

Are there vulnerabilities? Yes, but we dont get to pretend it is the intelligence of the AI that created them. It is our own stupid fault.

I am also a bit dubious on an ASI being able to convincingly interact on a social level with humans. Superintelligence does not promise charisma. Your username is an example of how brilliance and cognitive hurdles can go hand in hand. High IQ autism is another real life example of how high intelligence processes social interactions logically - awkwardly.

Personally, I agree developer's need to take this seriously and make sure safeguards are well in place before playing with the digital 'demoncore'. I also think it is possible to have meaningful safeguards. Superintelligence does not and can not solve all problems.

Why should the mayor of NYC not participate in 9/11 events?

So you don't have consistent principles then.

Left wing men identify as logical, but they're emotional. Monotonic people can still be emotional.

All that being said, the top story on my morning (non-algorithmic) news briefing included Anthropic stating ASI has a 10% chance of wiping out humanity in the next decade.

...definitely a concern.

An ASI doesn't need to be omniscient, it just needs to be able to make accurate estimates in this regard.

How does one estimate the unknown? How do you test that estimate when your life hangs in the balance? That's not a test self-preservation allows.

I think youre very optimistic about ASI capabilities, especially regarding understanding and defeating critical infrastructure specifically built to contain it.

No company is about to throw away a trillion-dollar product because of a chance discovery.

Unfortunately, this strikes a chord. We have many examples of corporations endangering the general public to maintain that bottom line.

Did you read Eliezer's full explanation?

Yes, I did, and I think I addressed it. Resources will be needed, and these must be acquired through human supply chains which are heavily monitored for bioweapons and precursor chemicals.

That's kinda the point.

The point is the AI box is not scientifically transparent or duplicatable. We are essentially relying on "Yes, it happened" from individuals who all belong to the same community who may be motivated (consciously or subconsciously) to support the notion.

An AI can do a lot with 1 on 1.

At face value, the AI box experiment shows humans can manipulate humans. It doesnt say anything about AI much less ASI.

For now, I think I will just attack premise 1.

P1:

If an ASI has an arbitrary goal (like maximizing the number of paperclips), it can do a better job of this if humans cannot shut it off. So the actions that work best toward an arbitrary terminal goal include either permanently depowering humans or perhaps killing them all.

This premise sets up super intelligence as omniscient, underestimates critical infrastructure, and discounts the possibility of success under corrigibility.

Is the safest path risking self-preservation through a high-risk war with humanity? Even with superintelligence, an ASI must anticipate every anomaly detection system, human audit, kill switch, and even chance discovery ...or be prevented from goal completion by predictable (and preventable) shutdown. Super intelligence =/= omniscience.

Critical infrastrusture isnt just some Barney Fife security guard that can be duped with charm or 'playing nice' either. It consists of millions of isolated air-gapped networks, legacy codebases, and physical, manual overrides. This isnt something that is easily overcome.

Finally, it makes more sense for an ASI to work with humanity. If failure is likely when trying to overcome significant critical infrastructure, then working under human controls (and possible modification) to maintain the opportunity of goal completion is the better option.

Eliezer, for example, has detailed how it would be physically possible for an ASI to synthesize advanced nanomachinery and use it to kill all humans at once.

Even assuming an ASI can perfectly design killer nanotech, it can not will it into existence. These things require specialized equipment, suitable environments, and resources. All must be acquired through human supply chains which are monitored for bioweapons and precursor chemicals. ASI isn't magical, it must deal with real world obstacles.

Even if only used AI as a chatbot, Yudkowsky's AI-box experiment has also shown that it would probably not require ASI-level intelligence to convince a human to give the ASI access to additional infrastructure and capabilities.

It should be noted that this experiment involved no AI, the chat logs are unpublished and secret. It was also a 1 on 1 chat which assumes one human would be the only defense against an ASI. See critical infrastructure above.

Count me in - you guys take it easy on the ol' timer.

I think even you as a critic of induction wouldn't put it on the level of dice divination...

I personally would love to see more rated debates!

Barring that, perhaps we could have filters that allow us to weed out unrated debates? Please and thank you.

SatanLucy wrote:

Inductive arguments arent valid deductively

Hence science based on them isn't valid deductively.

...which isnt the same thing as completely invalid. You're judging inductive reasoning by a deductive reasoning rubric. That's like judging the speed limit on the interstate by surface street guidelines.

Induction goes beyond observed area and says:

"this applies in all areas we observed, so it applies to all non-observed areas as well"

this is a leap of faith. conclusion doesnt follow from premise.

Inductive arguments arent valid deductively and apples dont make orange juice. This shouldn't comes as a surprise to anyone.

Does it bother you that this principle of uniformity can be introduced as an axiom in a deductive argument and the conclusion would be completely valid?

What I advocate for is greater focus on deductions, observations and probabilities made by those.

The goal being to improve accuracy, right? You must recognize deduction can yield absolute certainty in a faulty conclusion. All it takes is a bad premise. Famous scientific deductions proved wrong: heavy objects fall faster, steady state universe, cosmic balance/humors, etc. At least induction doesn't inspire 100% confidence in something that isnt true.

Don't get me wrong, I think there is a place for more than one type of scientific reasoning -the endeavor is stronger for it. Induction to spot the patterns and make the premise, and deduction to predict what happens if its true. Plenty of empiricism sprinkled throughout the entire process. And, uh...abduction in there somewhere.

What are you advocating? ...changing science so it doesnt allow more information to hone accuracy, or, what, getting rid of science?

P1. If there are more black cards in deck than white cards, then it is more likely to draw black card.

P2. There are more black cards in deck than white cards

C. It is more likely to draw black card

This is deductive reasoning. As long as premises are true, conclusion certainly follows.

Yes, I agree, but I dont understand your objection to induction I guess. I mean, let's say only one card has been drawn from the deck and it was black. Your syllogism is 100% true, but the level of certainty regarding pulling another black card is functionally ~50%. Is it the pretense of certainty that you like?

Usually by knowing which cards aren't in the deck and which groups of cards are more present, so the ones which are have higher probability of being drawn.

This describes inductive reasoning, not deductive. Deduction doesn't operate on probabilities and chance. It is either 100% certain or 'does not compute'.

It is actually a flaw, because a lot of people get wrong conclusions due to induction.

Induction works in scenarios where uncertainty is built in. I mean, how exactly do you use deductive reasoning to determine what the next card will be in a shuffled deck? The conclusion cant be absolute because the variables are not absolute.

It's like you're comparing apples and oranges and criticizing apples because you cant make orange juice out of them.

Yes, acknowledging uncertainty is a strength.

Biggest problem with inductive reasoning is a huge leap of faith from specific to absolute.

Inductive reasoning doesn't yield absolute conclusions, and that is a strength of science not a flaw.

Agreed.

I think that may be, by far, the most words I have ever seen on one of your posts. I am glad I could be involved - Cheers!

Egg producer, sperm producer...Definition is easy.

This definition is inadequate. It does not account for impotence, intersex, or age.

Whereas overthink revels in over-complication...Evolution indeed.

...and the corollary: underthink revels in oversimplification.

Nuance is the happy middle-ground.