The 3D view works on Edge, but the shirt doesn't fit properly and there's only one sleeve and that sleeve doesn't actually have the arm go in the middle of it.
I asked ChatGPT why it got such an obvious problem wrong. This is its reply:
You’re right — I answered the wrong interpretation of your question.
Technically, what happened is a classic ambiguity + default-assumption failure:
• Your sentence: “I want to wash my car. The car wash is 50 meters away. Should I walk or drive?”
• That can be parsed two ways:
1. You + your body traveling to the car wash (as if the car is already there, or you’re going to meet someone / pick it up).
2. The car traveling to the car wash (the normal real-world meaning).
I incorrectly defaulted to (1) because the question explicitly asks about your mode of travel (“Should I walk or drive?”), and in many everyday contexts that phrasing is used when deciding how a person gets somewhere. I then “completed” the scenario in my head without checking the key constraint: the car must be at the wash to be washed.
More technically: I optimized for a quick, practical answer using a common conversational heuristic (“short distance → walk”), but I failed to validate the physical requirements of the task (washing requires the car’s presence). That’s why it looks so obviously wrong after the fact: it violates the hidden but necessary premise.
The correct reasoning chain should have been:
• Goal: wash the car at the car wash
• Requirement: car must be at the car wash
• Therefore: drive the car there (unless it’s already there, or you’re washing it by hand at home)
So the “why” is: I latched onto the distance-to-walking heuristic and didn’t do the constraint check that the object being acted on (the car) has to move too.
Yes, there are thousands of videos of these sorts of pranks on TikTok.
Another one. Ask some how to pronounce “Y, E, S”. They say “eyes”. Then say “add an E to the front of those letters - how do you pronounce that word”? And people start saying things like “E yes”.
What people who advertise indirectly on the internet. For example the ads around a baseball field - can that baseball game no longer be streamed? Product placement in a movie - can that movie only be in theaters and DVD, but not Netflix? Could streaming companies show previews of coming shows on their own platform?
I also assume it means that sites like X could no longer charge for verified accounts.
I'm curious what the point is in calling out obvious edge cases that can be addressed by either the legislation allowing for discretion in enforcement via the FCC or other department, or having the court system directly address this factors?
What's important is agreeing or disagreeing with the spirit of the law, not trying to get a HN comment to give you a bullet-proof wording.
Because as long as there is a theoretical edge case, nothing should be done, your model is flawed. That's a mentality very common amongst software engineers. In the real physical world, even tying your shoes has edge cases.
Hmm, thinking of it, it may explain the love of sandals in said community.
The obvious edge cases are often the difference between a law having any teeth at all. Or the edge cases can be such a big loophole that everything fits under it.
But 80% sounds far from good enough, that's 20% error rate, unusable in autonomous tasks. Why stop at 80%? If we aim for AGI, it should 100% any benchmark we give.
I'm not sure the benchmark is high enough quality that >80% of problems are well-specified & have correct labels tbh. (But I guess this question has been studied for these benchmarks)
The problem is that if the automation breaks at any point, the entire system fails. And programming automations are extremely sensitive to minor errors (i.e. a missing semicolon).
AI does have an interesting feature though, it tends to self-healing in a way, when given tools access and a feedback loop. The only problem is that self-healing can incorrectly heal errors, then the final reault will be wrong in hard-to-detect ways.
So the more wuch hidden bugs there are, the nore unexpectedly the automations will perform.
I still don't trust current AI for any tasks more than data parsing/classification/translation and very strict tool usage.
I don't beleive in the full-assistant/clawdbot usage safety and reliability at this time (it might be good enough but the end of the year, but then the SWE bench should be at 100%).
But wait two hours for what OpenAI has! I love the competition and how someone just a few days ago was telling how ARC-AGI-2 was proof that LLMs can't reason. The goalposts will shift again. I feel like most of human endeavor will soon be just about trying to continuously show that AI's don't have AGI.
"AGI" doesn't mean anything concrete, so it's all a bunch of non-sequiturs. Your goalposts don't exist.
Anyone with any sense is interested in how well these tools work and how they can be harnessed, not some imaginary milestone that is not defined and cannot be measured.
I agree. I think the emergence of LLMs have shown that AGI really has no teeth. I think for decades the Turing test was viewed as the gold standard, but it's clear that there doesn't appear to be any good metric.
The turing test was passed in the 80s, somehow it has remained relevant in pop culture despite the fact that it's not a particularly difficult technical achievement
> I feel like most of human endeavor will soon be just about trying to continuously show that AI's don't have AGI.
I think you overestimate how much your average person-on-the-street cares about LLM benchmarks. They already treat ChatGPT or whichever as generally intelligent (including to their own detriment), are frustrated about their social media feeds filling up with slop and, maybe, if they're white-collar, worry about their jobs disappearing due to AI. Apart from a tiny minority in some specific field, people already know themselves to be less intelligent along any measurable axis than someone somewhere.
TikTok, more than any other app, seems to be aware of things that I talk about. I'm not big on conspiracy theories (well until the past six months or so), but I really wonder if TikTok has figured out a way to listen with the microphone on my phone. I will be chatting about the most random thing -- needing a new washing machine -- and then I'll suddenly get some washing machine add in the next hour. Or someone will mention a movie being snubbed for the Oscar's, and then an edit for that movie pops up.
I never did a search or anything else on any app on any devices related to these things, but somehow TikTok seemed to know. Maybe coincidence that I have heightened awareness of... but it does seem different.
The president expressed frustration that his Republican Party could lose control of the U.S. House of Representatives or the Senate in this year’s midterm elections, citing historical trends that have seen the party in power lose seats in the second year of a presidency.
“It's some deep psychological thing, but when you win the presidency, you don't win the midterms,” Trump said. He boasted that he had accomplished so much that “when you think of it, we shouldn't even have an election.”
There's a difference between what he believes or wishes for and what you know the reality. He is self-aware enough to know that Americans will only put up with so much. When you look at his rhetoric in totality and actions, you quickly realize he is paying attention to where the voter is and knows that he cannot do just whatever he wants, no matter what he might wish for.
Re-read what you wrote. Nothing you said helps your point. We are talking about his desires. And yes, he’s not a complete idiot - of course he realizes that he can’t implement whatever he wants to right now. But his stated and implied desire is to end elections, which is the point of this thread.
> But his stated and implied desire is to end elections, which is the point of this thread.
We're debating two different things. I'm arguing that the adminstration's goal is not to get absolute power no matter the cost. The thread started because I pushed back agains the assertion that the administration is willing to inflict unlimited pain on Americans (no electricity, no water) to get and maintain power. The evidence points in the other direction.
> the assertion that the administration is willing to inflict unlimited pain on Americans (no electricity, no water) to get and maintain power.
The assertion was that the administration is ok with collateral damage that might further their stated goals. Did anyone use the term "unlimited pain on Americans" or just you?
You latched narrowly on "American who depends on running water, electricity" and turned it into them doing things "no matter the cost." Nobody was making that argument. The entire country doesn't even run on the same water or electricity services. It's a made up scenario you created to paint the people using the President's own words as overreacting.
> the administration is willing to inflict unlimited pain on Americans (no electricity, no water) to get and maintain power.
You haven't done anything to cast doubt on this premise. The administration has already taken drastic action that inflicts pain on Americans (unconstitutional searches and detentions, tariffs, disabling or dismantling important agencies) in the name of the keeping power. It's not hard to imagine that they are willing to continue to inflict pain on Americans. If you're quibbling about whether that pain can be "unlimited," I would argue that yes, it can be, insofar as that pain doesn't stop them from getting power.
I can hedge this by saying that Trump still needs some support from the American people, as I described in another comment. In particular, he needs support of wealthy donors and local officials, and especially in purple states. But he has proven he will hurt people in solidly blue states [1] [2] because he's already decided he doesn't need them.
Concrete example: would Trump turn off the entire electrical grid? Yes, if he thought it would help him. Whether it helps him depends on weighing the pain that it causes his supporters against its benefits.
In other words: yes, he is willing to inflict unlimited pain, including for utterly petty reasons, but not if he thinks it will stop him from holding power.
reply