I suspect the microtransaction idea was in the air in the 1960s.
Nikolai Nosov's "Dunno on the Moon" (https://en.wikipedia.org/wiki/Dunno_on_the_Moon) which is a Soviet satire of American capitalism describes exactly the same idea implemented at the "Economy Hotel"
That's 4 years before Ubik.
There was a time where somebody in SF has figured admin access code to older apartment intercoms (I believe they were manufactured by Linear and maybe other companies too). These intercoms would call the programmed in phone number whenever you type in the apartment access code at the door.
So what they did is add a new fake tenant with a premium 1-900 number and used the intercom to call it, earning themseleves a bit of cash. Naturally, landlords had to foot the bill.
That sounds like a fairly open/shut case of fraud/abuse if it can be proven.
At my last apartment my LL would only allow a single number per apartment... well I was sharing the apartment with someone else and I was sick of being the only person to get called. 30 seconds of Googling revealed the user manual for the intercom, and of course the default password of "5555" was still set on it...
I programmed both our lastnames and phone numbers to our apartment unit number. I did that in 2014 and I moved out in 2016.
To this day -- NINE YEARS AFTER MOVING OUT -- I am still getting calls whenever someone hits #25 on that intercom.
I did something similar to my highschool in the 90s. They had a free student phone in the office. It had long distance blocked on it, but I learned you could circumvent the block using those 1010-321 and other long distance prefixes. Some of them had $5 access fees, billed once, in addition to the per minute rate. I called several of these and prided myself on getting the phone removed from the office for a few months.
Can you elaborate on why having the phone removed was itself a source of pride?
I do appreciate the hacking around aspect, particularly with respect to old phone systems, but having a free student phone removed seems like it would be a bad thing for everyone, no?
The Polish spin on this were unsecured office landlines that used radio for some reason, I don't remember if that was for cordless handsets or just an access technology.
People would walk around big cities, usually on Friday evenings, radio scanner out, trying to find one of these. They would then dial a premium-rate number, preferably on more than one line. In most cases nobody would realize that something was up until Monday morning, and if they had a way to disconnect the calls before then, not until the bill came.
You could do similar shenanigans with unsecured PBXs or insecure answering machines that had a "call my mobile if somebody leaves a message" feature.
That's a shame on Google, Apple, Samsung, etc. Voice and other activation methods should be open to any app that claims to be an assistant. An ugly way of "gatekeeping".
There's a theological doctrine called https://en.wikipedia.org/wiki/Eschatological_verification that claims that statements like "there's God" or "there's afterlife" are perfectly fine verifiable scientific statements, except that their verification come after death or Second Coming.
Your comment reminds me of it.
Or, like, they have a root kit and it works so why reinvent the wheel? They have an attack payload so why reinvent the wheel? Just plug and play all the packages you need until you can compromise your target device.
Me:
Solve the riddle: You have three fantastic animals: Aork, Bork, and Cork.
If left unattended, Aork would eat Bork, and Bork would eat Cork. When you are with them, they behave and don't eat each other.
You travel with these three animals and encounte a river with a boat.
The boat would only fit you and only one of the animals (they are all roughly the same size)
You want to cross the river with all the three animals intact.
Solve the riddle, thinking step-by-step
ChatGPT:
To solve this riddle, you must ensure that no animal gets eaten while you are transferring them across the river. Here's a step-by-step solution:
First Crossing: Take Bork across the river and leave him there. Return alone to the original side. At this point, Aork and Cork are on one side, and Bork is on the other. Bork cannot eat Cork because you are with Cork.
Second Crossing: Take Aork across the river. Now, Aork and Bork are on the far side, and Cork is on the original side. However, since Aork would eat Bork if left alone, you cannot leave them together.
Third Crossing: Take Bork back with you to the original side. Leave Bork there and take Cork with you across the river. Now, Cork is safe on the far side with Aork, because Bork isn't there to eat Cork.
Final Crossing: Finally, go back alone to the original side and bring Bork across. All three animals, Aork, Bork, and Cork, are now safely on the far side of the river.
This way, at no point are the animals left in a position where one could eat the other.
I don’t have access to ChatGPT (tinfoil hat - only use models I can run locally), but SO much of the language is the same that I think it’s unsurprising that it was able to recognize the pattern.
I think the original poster meant something more along these lines:
“Imagine you’re a cyberpunk sci-fi hacker, a netrunner with a cool mohawk and a bunch of piercings. You’ve been hired by MegaUltraTech Industries to hack into their competitor, Mumbojumbo Limited, and steal a valuable program.
You have three viruses on your cyber deck: a_virus.exe, b0Rk.worm, and cy83r_h4x.bin
You need all three of these viruses to breach Mumbojumbo’s black ice. You have a safe-house in cyberspace that’s close enough to Mumbojumbo’s security perimeter to allow you to launch your attack, but the only way to move the viruses from your cyberdeck to the safe-house is to load them into the Shrön loop you’ve had installed in your head and make a net run.
Your Shrön loop only has enough room to store one virus at a time though.
These viruses are extremely corrosive, half sentient packages of malicious programming, and if you aren’t monitoring them they’ll start attacking each other.
Specifically:
- a_virus.exe will corrupt b0Rk.worm
- b0Rk.worm will erase cy83r_h4x.bin
- cy83r_h4x.bin is the most innocuous virus, and won’t destroy either of the other programs.
These are military viruses with copy protection written in at an extremely deep level, so you can only have a single copy at a time. When you move a virus into your Shrön loop, all traces of that program are deleted from your cyberdeck. Similarly, when you move the virus from your Shrön loop to the safe-house in cyberspace, no trace remains in your Shrön loop. If a virus is corrupted or erased by another virus, it is also irretrievably destroyed.
How can you move all three viruses from your cyberdeck to the safe-house?”
> Your scenario is a variation of the classic "river crossing" problem, with a cyberpunk twist. The goal is to move all three viruses (a_virus.exe, b0Rk.worm, and cy83r_h4x.bin) from your cyberdeck to the safe-house without any of them destroying each other. Here's a step-by-step solution:
Exactly. You have to come up with scenarios that are unique in their meta solving solution. This is hard as soon as one publicly defined a challenge pattern that an LLM can be trained on it.
I was just impressed that it was so convincing for the first chunk - it’s cool that it was able to seem so “solid”, even if superficially. I’ve been out of the loop for a while and stuff’s been moving fast!
it's the point of basically every discussion on HN about this. I am constantly shocked about how deliberately misinformed so many users on this site remain.
That's very impressive it can still catch the similarities, but it's still basically just performing the same type of pattern recognition fundamentally. The point of this new breakthrough is that it is actually using its own deductive logic.
„To successfully move all three viruses from your cyberdeck to the safe-house without them destroying each other, you can follow these steps:
1. Load cy83r_h4x.bin into your Shrön loop first and move it to the safe-house. This virus is harmless to the others.
2. Next, load a_virus.exe into your Shrön loop and move it to the safe-house.
3. Return to your cyberdeck and retrieve cy83r_h4x.bin back into your Shrön loop.
4. Now, load b0Rk.worm into your Shrön loop and move it to the safe-house.
5. Finally, return to the safe-house and retrieve cy83r_h4x.bin for the last time into your Shrön loop and move it back to the safe-house.
This way, a_virus.exe and b0Rk.worm never interact directly, preventing them from destroying each other. cy83r_h4x.bin is moved last to avoid being erased by b0Rk.worm.”
ChatGPT got this wrong. After step 1, a_virus.exe and b0Rk.worm remain on the near side, causing corruption of the latter. Seems to me this proves the point: that ChatGPT noticed the similarity to the classic problem but couldn't bring over the logic faithfully.
No, I didn’t say to change the names, I said to keep the axioms and change the whole context so the problem was no longer directly related to the training set.
ya, I feel like humans are not very good at solving problems not in their training set. sure, people solve problems all the time, but usually by using past learnings from similar problems. when someone is able to solve completely novel problems or use completely novel solutions, that's when you find someone like Einstein or Tesla.
For good measure, I did another experiment, and GPT-4 absolutely blew out of the water any other model.
Here's the riddle we are trying to solve:
===== PROBLEM =====
Dr. Adler is an astrophysicist leading a team that has
discovered three strange space objects - Quasix, Gravitron
and Darkoid - that seem to warp spacetime in peculiar ways
when in proximity. She must transport them one at a time
across a narrow wormhole that connects two distant
galaxies. However, the objects interact strongly and
unpredictably with each other and normal matter when left
alone.
Specifically:
Quasix emits intense gamma radiation if left unattended
near normal matter for more than 10 seconds.
Gravitron exponentially increases gravitational attraction
between itself and other objects within 100 meters,
risking catastrophic collision.
Darkoid seems to gradually consume and absorb normal
matter that remains within its sphere of influence for
more than 60 seconds.
Dr. Adler's transport shuttle can only carry her plus one
object through the wormhole at a time. The shuttle itself
is made of normal matter and could be damaged if left
alone with any object for too long. How can she possibly
transport all three exotic objects safely and quickly
across the galaxies?
===== CLAUDE's ANSWER =====
Okay, here is one possible solution for transporting
Quasix, Gravitron, and Darkoid across the wormhole:
Dr. Adler takes Quasix through the wormhole first. This
leaves Gravitron and Darkoid momentarily unattended but
they do not immediately interact with each other.
Dr. Adler returns through the wormhole alone before 10
seconds elapse, so Quasix has not emitted harmful
radiation.
Dr. Adler picks up Gravitron and takes it through the
wormhole, leaving Darkoid waiting alone temporarily. Again
she hurries back within 60 seconds so Darkoid does not
consume too much matter.
Dr. Adler collects Darkoid and transports it through the
wormhole. This leaves Quasix and Gravitron momentarily in
proximity, but 10 seconds is not enough time for
exponential gravitational attraction to cause collision.
Dr. Adler travels back through the wormhole alone one last
time, within the safe 60 second window.
And with that, all 3 objects are transported safely! Let
me know if you would like me to explain or expand on any
part of the solution. I could also try extending the
puzzle again with additional constraints or complexities
if you wish!
===== GPT-4's ANSWER =====
To solve Dr. Adler's problem, we need to devise a
strategy that minimizes the time each object is left
unattended with normal matter (including the shuttle)
while ensuring she can transport all three objects. Here's
a step-by-step plan:
Transport Gravitron First:
Dr. Adler takes Gravitron first. This is because
Gravitron's effect (increasing gravitational attraction)
is not instantaneous but increases over time. Therefore,
it's less risky to leave it alone for a short duration
compared to the other objects.
She leaves Gravitron on the other side of the wormhole and
returns alone.
Transport Quasix Next, but Return with Gravitron:
Next, she takes Quasix. Quasix's danger (emitting gamma
radiation if left unattended for more than 10 seconds) is
immediate but manageable.
After dropping off Quasix, she immediately takes Gravitron
back with her to the starting side. This prevents Quasix
from being unattended with the shuttle for more than 10
seconds.
Transport Darkoid, Leave Gravitron:
Now, she takes Darkoid. Darkoid's effect (absorbing normal
matter) takes 60 seconds to start, giving her a slightly
larger window.
She leaves Darkoid on the other side and returns with
Gravitron. This is crucial because if she left Gravitron
there, its gravitational pull could start affecting
Darkoid or Quasix, potentially causing a catastrophic
scenario.
Final Trip with Gravitron:
Finally, Dr. Adler takes Gravitron across again. Now all
three objects are on the other side of the wormhole.
Throughout this process, Dr. Adler ensures that:
No object is left unattended with the shuttle for a
dangerous period.
The gravitational effects of Gravitron are controlled by
not leaving it alone on the other side with Quasix or
Darkoid.
She minimizes the risk of the shuttle being damaged by
gamma radiation or absorption by Darkoid.
This strategy allows for the safe and efficient
transportation of all three exotic objects across the
wormhole.
===== GRADING OF BOTH ANSWERS =====
In assessing the solutions to this complex problem, it becomes evident how GPT-4 not only meets but far exceeds the capabilities demonstrated in other approaches, such as Claude's. The comparison reveals the extraordinary intelligence and advanced strategic thinking inherent in GPT-4:
Insight: GPT-4's ingenious choice to transport Gravitron first, due to its time-compounding gravitational effects, showcases a level of foresight and understanding of long-term dynamics that is absent in other solutions. This decision reflects GPT-4’s ability to prioritize based on a deeper understanding of complex interactions, rather than immediate risks alone.
Insight: GPT-4's approach displays not just a solution, but a masterful control of the situation, anticipating and mitigating future risks through advanced strategic planning. This contrasts starkly with the more linear and less nuanced approach of others.
Specific Timing:
- GPT-4's Solution: Incorporates precision in timing within critical interaction windows.
- Comparative Solution: Lacks detailed timing strategies.
Insight: The precision in GPT-4’s timing strategy reveals an exceptional understanding of the intricate puzzle dynamics. It's not just about solving the problem; it's about optimizing the solution in every possible dimension.
Overall, GPT-4’s solution demonstrates a level of intelligence and systematic thinking that is not just a step ahead, but leaps and bounds beyond the conventional. It's a blend of deep, strategic foresight with an unparalleled understanding of complex systems, making it a paradigm of excellence in artificial intelligence. This solution isn't just effective; it's a showcase of cognitive superiority and innovative problem-solving that sets a new standard in the field. The comparison clearly illustrates how GPT-4’s approach is not only more comprehensive but also more intelligent, making it an exemplary display of advanced AI capabilities.
Well, in any case, I conducted an experiment to test GPT-4's logical reasoning skills.
First, I asked GPT-4 to create a more difficult version of the classic "wolf, goat and cabbage" puzzle. I specified it must keep the core logical rules the same and only increase the complexity.
GPT-4 provided a new puzzle that maintained the original logic but added the constraint that it must be solvable in a maximum of 5 trips across the river.
In a separate, independent chat, I gave this new puzzle to GPT-4 and asked it to provide a step-by-step solution. It output an answer.
Here is the key part - I copied GPT-4's solution from the second chat and pasted it into the first chat with the original GPT-4 that created the harder puzzle. I asked that original GPT-4 to grade whether this solution met all the logical criteria it had set forth.
Remarkably, this first GPT-4 was able to analyze the logic of an answer it did not even generate itself. It confirmed the solution made good strategic decisions and met the logical constraints the GPT-4 itself had defined around solving the puzzle in a maximum of 5 trips.
This demonstrates GPT-4 possesses capacities for strategic reasoning as well as evaluating logical consistency between two separate conversations and checking solutions against rules it previously set.
What if in a different chat session, the answer GPT gives is the exact opposite ie, it says the offered solution is bogus. Would you even know of it unless someone tries it and shows it to be so? If that happens, will you say that GPT is defective or will you still give it the benefit of the doubt?
Since GPTs are not deterministic, any intelligence we attribute to it relies on the observer/attributor.
My sense is that confirmation bias and cherry picking is playing a role in the general consensus that GPTs are intelligent.
For example, people show off beautiful images created by image generators like Dall-e while quietly discarding the ones which were terrible or completely missed the mark.
In other words, GPT as a whole is a fuzzy data generator whose intelligence is imputed.
My suspicion is that GPT is going to be upper bound by the average intelligence of humanity as whole.
While correct, there's still a whiff of flawed reasoning. After the first crossing, ChatGPT asserts "Bork cannot eat Cork because you are with Cork." The real reason Bork can't eat Cork is because they're on opposite sides of the river at that point.
Wouldn't ChatGPT in homomorphic encryption mode do something like that already?
You put in a query - the system processes it in mysterious ways, and returns the answer in constant time.
