Sean Caroll has talked about a few word puzzles he asked chatgpt and gpt4 or whatever and they were interesting examples. In one he asked something to the effect of “if i cooked a pizza in a pan yesterday at 200 C, is it safe to pick up?” and it answered with a very wordy “no, its not safe” because that was the best match of a next phrase given his question, and not because it can actually consider the situation.
Me: If I cooked a pizza in a pan yesterday at 200 C, is it safe to pick up?
Claude: Yes, if you cooked a pizza in a pan yesterday at 200°C (392°F), it is completely safe to pick up now. Once a pan has cooled down after cooking, which usually takes no more than an hour or two, it returns to a normal temperature and can be safely handled.
The high heat during cooking is needed to bake the pizza properly, but that heat dissipates fairly quickly after removing the pan from the oven. Unless you’re picking up the pan immediately after taking it out of the oven, there’s no risk of burning yourself.
So, a day later, your pizza pan will be at room temperature and perfectly safe to touch and handle without any precautions.
Bonus:
Me: Is it safe to eat the pizza in the pan after I pick it up?
Claude: If you cooked the pizza yesterday and left it in the pan at room temperature, it is not safe to eat today. Cooked food should not be left at room temperature for more than 2 hours, as harmful bacteria can grow and multiply, leading to foodborne illnesses.
According to food safety guidelines, leftover pizza should be refrigerated within 2 hours of cooking. If left out longer, it’s best to discard it to avoid the risk of food poisoning.
If you did refrigerate the pizza within that safe window, it would typically be safe to eat for up to 4 days, though the quality is best if consumed within 2-3 days. To reheat, it’s best to use an oven, skillet, or air fryer rather than the microwave, which can make the crust soggy.
In summary, if your pizza was left in the pan at room temperature since yesterday, it is not safe to consume and should be discarded.
Versions matter in software, and especially so in LLMs given the rate of change.
And nobody on the internet is asking obvious questions like that, so counterintuitively it’s better at solving hard problems. Not that it actually has any idea what it is doing.
EDIT: Yeah guys, I understand that it doesn’t think. Thought that was obvious. I was just pointing out that it’s even worse at providing answers to obvious questions that there is no data on.
Unfortunately it doesnt have the capacity to “solve” anything at all, only to take a text given by the user and parse it into what essentially amount to codons, then provide other codons that fit the data it was provided to the best of its ability. When the data it is given is something textual only, it does really well, but it cannot “think” about anything, so it cannot work with new data and it shows its ignorance when provided with a foreign concept/context.
edit: it also has a more surface-level filter to remove unwanted results that are offensive
Sean Caroll has talked about a few word puzzles he asked chatgpt and gpt4 or whatever and they were interesting examples. In one he asked something to the effect of “if i cooked a pizza in a pan yesterday at 200 C, is it safe to pick up?” and it answered with a very wordy “no, its not safe” because that was the best match of a next phrase given his question, and not because it can actually consider the situation.
Let’s try with Claude 3 Opus:
Bonus:
Versions matter in software, and especially so in LLMs given the rate of change.
Yep, still lacking any sapience.
And nobody on the internet is asking obvious questions like that, so counterintuitively it’s better at solving hard problems. Not that it actually has any idea what it is doing.
EDIT: Yeah guys, I understand that it doesn’t think. Thought that was obvious. I was just pointing out that it’s even worse at providing answers to obvious questions that there is no data on.
Unfortunately it doesnt have the capacity to “solve” anything at all, only to take a text given by the user and parse it into what essentially amount to codons, then provide other codons that fit the data it was provided to the best of its ability. When the data it is given is something textual only, it does really well, but it cannot “think” about anything, so it cannot work with new data and it shows its ignorance when provided with a foreign concept/context.
edit: it also has a more surface-level filter to remove unwanted results that are offensive
you dont get the point, do you?