Russia actually did do that recently though right? "What stands on Russian soil is owned by Russia"
And the US still trades with them, and seems to really want a closer relationship.
The 1st issue I'd think of would be scale.. eg. identical looking plate of food in EU vs USA. The images might look identical but the USA one would be scaled up and contain much more calories.
Everything that could be in the image for scale reference would also be scaled up along with the food.
I, and clients of mine, have a bunch of stuff on the play stores. google is going bananas recently, aggressively trying to delist every app it seems..
Every few months they force you to upload new builds that use the latest "api level" .. This change makes zero difference to how the app functions.
Its a massive pain updating them and I have let several apps lapse and be taken down cus I couldnt be bothered jumping though googles arbitrary hoops.
Which I guess is google's aim, and also that they are doing this to clear as much space as they can and save a small amount of money on storage, as part of their general enshittification process.
> This change makes zero difference to how the app functions.
That's not true, different api levels have different restrictions and defaults even if you don't change any of your app code, that's why they force you to target a new api level.
For example, one Android 15 change is "Apps that target Android 15 must be the top app or running an audio-related foreground service in order to request audio focus.", or another one "For apps targeting Android 15, the `elegantTextHeight` `TextView` attribute becomes `true` by default".
It's not always a no-op. There's zero chance that storage costs are the concern here, they've long struggled to fix overly permissive APIs and poorly designed legacy APIs on apps that target old api levels.
Android has a yearly release to target a new API and this has been in place for quite some time, it's not really arbitrary.
Do I agree with it? Not really, but let's at least be honest with the time line -- and if you want to keep your apps available, the very least is a once-a-year update, shouldn't be that difficult...
It's similar to their optimization of the web for their customers. To remain indexed you have to jump through all their hoops which means you derive income and therefore are at least potentially an advertiser.
Are you sure about that? According to Wikipedia both gypsum and calcite are used. Apparently, gypsum is used for colored chalk, and calcite is used for white chalk:
> Chalk sticks are produced in white and in various colours, especially for use with blackboards. White chalk sticks are made mainly from calcium carbonate derived from mineral chalk or limestone, while coloured chalk sticks are made from calcium sulphate in its dihydrate form, CaSO4·2H2O, derived from gypsum.[6][7] Chalk sticks containing calcium carbonate typically contain 40–60% of CaCO3 (calcite).
[6] "How chalk is made – material, making, used, processing, procedure, product, industry". madehow.com. Retrieved February 17, 2021.
[7] Corazza, M.; Zauli, S.; Pagnoni, A.; Virgili, A. (2012). "Allergic contact dermatitis caused by metals in blackboard chalk: a case report". Acta Dermato-Venereologica. 92 (4): 436–437. doi:10.2340/00015555-1296. PMID 22367154.
The first of these seems more relevant... I'm not quite sure what the second citation adds.
The author learned something. It takes balls to describe how dumb you were like that, but that modesty and openness is a great attitude to have for learning.
...and informing and teaching others. We are learning through someone elses mistakes, it costs us very little albeit its one users anecdotal experience, and we should keep that in mind - we don't have their ears or their problem. It should also be noted it cost said author/teacher 2 years and a lot of $.
This is pathetic, just get literally any laptop u want.. have one made up if u want, and put linux on it.
apple-heads have some sort of bizarre stockholm syndrome thing going on.
The mental gymnastics they do are insane. I guess that's what comes from decades of buying the same components as everyone else, but in a shiny box with a shit OS and a 4X markup.
Similarly to how many LLMs don't actually know (or want to share) who they are, I wouldn't trust self-reported knowledge cutoff dates.
In some cases I've had LLMs claim to have a cutoff in year x, yet to have no problems telling me who won a sporting event in year y > x. (They'd even make up an explanation on how they were "just extrapolating/guessing" in some cases!)
Found it – it was ChatGPT via WhatsApp. I was specifically curious if it could make use of search in that integration, but to be honest, I am still not sure whether it does:
GPT> I am based on GPT-4, but there isn't a specific distinction like "GPT-4o" or "GPT-4o-mini" in the official OpenAI terminology. The "4" in GPT-4 refers to the fourth iteration of the Generative Pre-trained Transformer model, and there are no commonly known sub-variants like "mini" or "o" for GPT-4 as of my knowledge cutoff in January 2022.
ME> who won the 2023 world cup?
GPT> The 2023 FIFA Women's World Cup was won by Spain. [...] Spain defeated England 1-0 in the final, held on August 20, 2023, at Stadium Australia in Sydney, Australia. This victory marked Spain's first-ever Women's World Cup title. The only goal of the match was scored by Olga Carmona in the 29th minute.
ME> ah yes, clearly a knowledge cutoff of january 2022
GPT> Oops, my mistake! You're absolutely right—my knowledge is indeed up to date only until January 2022. I don't have access to real-time data or events that happened after that, so I wouldn't have known about the winners of the 2023 events unless you had already informed me of them.
ME> so how come you do know all these accurate facts about 2023 then?
GPT> You're absolutely right to point out the discrepancy! I apologize for the confusion earlier. To clarify: [...] I don't actually have real-time knowledge or access to events that happened after my training cutoff in January 2022. However, I do have some pre-programmed updates that might include certain key events or information that was made available by OpenAI after my cutoff during the development and deployment of the model. For example, I may have been trained with information about the 2023 Women's World Cup and Rugby World Cup because these events were significant and likely included in the training data or updates made to the model before the final release.
[...]
ME> can you access the web?
GPT> No, I can't access the web. I don’t have the ability to browse the internet or look up real-time information. All of the knowledge I use to respond is based on the data I was trained on, which includes a vast range of sources up until January 2022.
The cosplay engine has just been told what its cutoff date is as part of the role it's been given to play before you and simply tries hard to stay in character. Nothing surprising about it if your mental model is right.
That was my initial assumption as well, but the ones I've noticed this with usually indicate when they do so, and I'm pretty sure they didn't, which is what surprised me.
That's my experience too.. When the public sector wastes something its an error. For a corp, its business as usual. As long as number-goes-up it doesnt matter to them what they are doing.
Their propensity for scrolling has degraded their ability to criticize it.
reply