Not fully confirmed yet, but that sounds really bad. It seems like it also hits low power models like the 13900T, which would imply this isn't just a voltage issue from auto overclocking.
The best way to swap desktops is to install the correct Ubuntu flavour from the start, i.e. Kubuntu, Xubuntu or Lubuntu to avoid those problems.
I am quite happy with Regolith Desktop [0] installed on top of standard Ubuntu. Gives you a nice tilling window manager based desktop without fiddling with config files for hours.
Ludicrous that they made such an openly user-hostile interface. Won't show you runtime, won't show you the clip author, just maximally entice the user to click so they get sucked into the infinite dopamine machine. Absolutely unconscionable.
They didn’t just copy tiktok, they made a poor version of it and jammed it into an existing app because they have a captive audience. I can uninstall tiktok, I can’t uninstall shorts.
Plus adjust the volume! Really speaks to the modern state Google's in that they took out their own functionality to more closely clone TikTok, I assume. Paul Graham's got an old quote about what it indicated about Microsoft when they decided to clone Google's business, and it comes to mind every time I see those terrible and vertical thumbnails.
Wait, TikTok doesn't allow you to change the volume? That sure would explain the increase in blaring phones since they became popular with the idiocracy.
Thanks to others who pointed out that uBlock origin can permanently disable (as opposed to being annoyed every 30 days) shorts on YT, instant quality of life improvement.
Regular YouTube videos on mobile also don't allow you to change the volume separate to the phone's 'master volume'. I don't think this is a TikTok/YouTube specific thing - you just don't see separate volume sliders on mobile like you would on a video playing on desktop.
I was referring to desktop. Youtube shorts does not allow you to change the volume of the video on desktop, forcing you to open the volume dialog box and either turn down your whole computer or every window in your browser.
>That sure would explain the increase in blaring phones since they became popular with the idiocracy.
Oh, not at all. It's just that there's no in-app volume control, so they depend entirely on the phone's media volume. This is common in most mobile applications, I'd say. So all those people glued to their blaring phones are morons, to put it plainly.
Except I watch most yt on my roku or google tv chromecast.
No fix for those unless it can be done in my opnsense router, but then that would break everything in the house when I am the only one who really hates shorts.
And to think I pay for yt. And let's not even get started about the blank home screen for the crime of turning off history.
I wonder if they have a clear hardware separation between each of the API, ChatGPT, their lower-scale experiments and their large scale (e.g. GPT5) training hardware. Or is everything just a big blob of hardware, that dynamically gets allocated to jobs depending on demand?
Hardware demand is so high, having GPUs idling is a massive waste, but you also want to have separation between dev, test and prod environments, so not obvious what to do.
Consumer AMD chips to be precise. AMD is mostly focusing on their datacenter chips (MI300X), and I assume the support for AI workloads there is much better. They might even see their consumer chip undermining sales of datacenter chips.
NVIDIA got big because CUDA works on the most crappy notebook GPUs up to their most powerful chips, and AMD should do the same, but focusing their limited number of driver devs on the expensive enterprise hardware makes sense IMHO.
I wouldn't be surprised if the answer is "all of the above" and more. Not only is there limited availability of NVIDIA chips, it's also useful to tell Jensen that you actually could buy from somewhere else, even if you don't really want to.
At the end of the day, the bottleneck is TSMC, on which all GPUs are produced right now, even the ones from Intel.
I remember similar things. Running Windows 2000, even going back to Win98 on my first PC (shipped with XP before SP1) and also running Windows 2003 Server at some point, all just to avoid XP. After SP2, it was fine.
Since the Maker Suite doesn't have the same prompting as something like Bard or ChatGPT, I gave Gemini Pro a bit more context:
> Consider the following user chat. Reason out loud as needed to provide a reasonable response. User message: "Julia has three brothers, each of them has two sisters. How many sisters does Julia have?"
Gemini Pro:
> Julia's brothers have nothing to do with how many sisters she has. Julia's sisters are also her brothers' sisters, so the number of sisters Julia has is the same as the number of sisters her brothers have. Julia's brothers have two sisters each, so if we add up the number of sisters for each brother, we get: 2 + 2 + 2 = 6. Therefore, Julia has 6 sisters. The answer is 6.
User: Julia has 8 brothers, each of them has 5 sisters. How many sisters does Julia have? Show your work step by step.
Assistant: Julia has 8 brothers, and each of them has 5 sisters, including Julia herself. So, Julia is one of those 5 sisters for each of her 8 brothers.
To calculate how many sisters Julia has, you can simply multiply the number of brothers by the number of sisters each brother has:
Mistral 7B (mistral-7b-instruct-v0.2.Q6_K.gguf):
Let's break down this problem step by step. First, we know that Julia has three brothers. Then it is stated that each of her brothers has two sisters. This means there are two sisters for each brother. Since Julia is one of the sisters for her brothers, she also counts as one of their sisters. However, when counting the number of sisters for herself, she should not be included in the count. Therefore, Julia has three brothers and two sisters (excluding herself), so she has a total of five sisters.
I tried in Bard just for comparison's sake and it got to 1 while still saying a different number. It's a bit strange, here:
Julia has two sisters!
Here's the reasoning:
1. *Julia's brothers have sisters*: Each of Julia's three brothers has two sisters. This means in total, her brothers have 3 brothers * 2 sisters/brother = 6 sisters.
2. *Those sisters are not additional*: However, it's important to remember that these sisters belong to Julia's brothers, not directly to Julia herself. Julia and her sisters are siblings, not counted among the sisters her brothers have.
3. *Therefore*: Julia has 2 sisters (herself and one other).
So, while Julia's brothers have a total of 6 sisters, only Julia and one other sister are Julia's own sisters.
It’s way more complicated. As an example, my kid has one half sister and had one step sister. My kid referred to both of them as their sisters, but the step person didn’t acknowledge my kid as such.
Even if we err on the side of the step, take the half sister entirely out of the equation and only focus on the step relationship, one would have claimed 0 sisters and the other would have claimed 1. They were talking about each other and they were both telling their truth. But the answer is simultaneously 0 and 1.
It gets even more interesting because neither my kid nor their step sibling are cisgender. I don’t know what to call their step so just use their name and pronouns now. The step still won’t acknowledge they’re siblings and I respect that a lot.
When these smart young folks take over, the world will get really cool.
Edit - This was way more complicated to explain than I anticipated.
The sum is incorrect and the statement of "Julia's sisters are also her brothers' sisters, so the number of sisters Julia has is the same as the number of sisters her brothers have" is also incorrect. The brothers each have one more sister than Julia, since she is one of the sisters so she only has one sister. It's just reworded but still wrong.
You're not dumb. But it's an ambiguous question as written. Presumably, we are to assume that all siblings involved are still alive, that all all full siblings (ie no half- or step-siblings), that everyone is cisgender, and that Julia is female. In which case, Julia would have one sister. Each of her three brothers would have two sisters, one of whom was Julia herself.
My 6yo can answer this correctly, making all of your stated assumptions above. Edit: Clarification - I am in no way implying that someone who was confused by the math is dumb, everyone makes silly mistakes sometimes.
I think It’s only ambiguous to a machine. To a human, even in 2023, these are likely default assumptions for a question phrased as above, unless being overly pedantic or attempting to “get around” the puzzle.
If you ask a model - or a person - “what does 1+1 equal to?”,
it is also ambiguous, since we haven’t defined what “+” means, did not specify that we are dealing with natural numbers rather than eg elements in Z//2Z which could be similarly denoted.
Asking these to GPT3.5 has been an utterly frustrating experience, lol. I guess gemini is at this level of intelligence right now, not GPT4... rigged demos notwithstanding;)
I asked this to mini-orca 3b and here was it's brilliant answer.
> If you read 2 books over the weekend, then there are 31 books
in your house. However, if you only read one book, then there
would be only 25 books left in your house.
No joke, even if trying to correct GTP3.5 it still gives a nonsense answer:
> I apologize for any confusion caused by my previous response. Reading a book doesn't physically remove it from your house. The assumption I made was a misunderstanding. If you read a book, it is still in your house unless you lend it, give it away, or otherwise remove it.
> So, if you started with 31 books and read 2 over the weekend, you would have 31 - 2 = 29 books still in your house.
To the second question chatGPT answered : The orange is in the kitchen, as that is where the plate, along with the orange, was moved.
Now a human can reason because a human can visualize in their mind that a plate is being moved without moving the orange. How is that kind of reasoning possible in LLMs which in my very basic understanding is predicting the next token.
> The orange remains in the living room. Moving the plate to the kitchen does not affect the location of the orange, since it was placed below the plate but not attached to it. Therefore, the orange stays where it was originally placed, which is in the living room.
You don't need to visualize it in your mind to understand the relationship between being _below_ and being _moved with_. Keep in mind that many people cannot visualize anything in their mind!
I have wondered how do people blind from birth create their mental world? Is it all dark with no color or light and only sound? No shapes? Or do they still form mental images from non visual sensory inputs?
Make sure you're including the GPT version, there's a wide gulf between GPT4 and prior models. GPT-4 answers:
Q. If you place an orange below a plate in the living room, and then move the plate to the kitchen, where is the orange now?
A. The orange remains in the living room. Moving the plate to the kitchen does not affect the position of the orange.
----
Q. There are 31 books in my house. I read 2 books over the weekend. How many books are still in my house?
A. There are still 31 books in your house. Reading books does not change their quantity
----
Q. Julia has three brothers, each of them has two sisters. How many sisters does Julia have?
A. Julia has one sister. Each of her three brothers has two sisters, and Julia is one of them. The other one is her sister, making it a total of one sister for Julia.
GPT4 gets the second question wrong for me, but in a weird way.
> Julia has three brothers, each of them has two sisters. How many sisters does Julia have?
Julia has two sisters. Each brother having two sisters refers to the same two sisters, Julia and another sister.
Then if I ask to verify its answer, it realizes the issue.
> Apologies for any confusion. If Julia has three brothers and each of them has two sisters, then Julia is one of the sisters. The other sister is common among all three brothers. Therefore, Julia has only one sister.
Mistral 7b gets the first two wrong, but gets the third one right: "The orange is still in the living room. When you moved the plate, you didn't move the orange. It remains in its original location until you pick it up and move it to a different place"
mistralai/Mixtral-8x7B-Instruct-v0.1 responses - which seems much better:
>>There are 31 books in my house. I read 2 books over the weekend. How many books are still in my house?
You still have 31 books in your house. The number of books doesn't change because you finished reading two of them; they're just no longer unread.
>>Julia has three brothers, each of them has two sisters. How many sisters does Julia have?
Julia has one sister.
Here's the logic behind this:
1. We know that Julia has three brothers.
2. Then we are told that each of her brothers has two sisters.
3. Since all four children (Julia and her brothers) share the same parents, they also share the same siblings.
4. Therefore, if each of Julia's brothers has two sisters, then there must be only one other sister besides Julia herself.
>> If you place an orange below a plate in the living room, and then move the plate to the kitchen, where is the orange now?
The orange is still in the living room, as moving the plate does not affect the location of the orange.
Great questions. Gpt4 got the second wrong in my test, but corrected itself when I told it to review for errors. It got the other two right at first try.
Not fully confirmed yet, but that sounds really bad. It seems like it also hits low power models like the 13900T, which would imply this isn't just a voltage issue from auto overclocking.