netruk44

If you're worried about losing access, and are willing to pay, you can sign up for an OpenAI account and use the OpenAI Playground with the 'text-davinci-003' model. I haven't tried using that model personally, but the model became available for public use around the same time ChatGPT came online, and they're both labeled as being in the GPT 3.5 family.

I would verify how similar the outputs are, but my trial credits have expired and I'd rather just use the free ChatGPT instead, hah.

I remember the Korok Forest in BOTW running at sub 20 fps back when I played it on Switch in handheld mode (I'm guessing at the fps). It was the only area I remember having performance issues, but there might have been other places.

I haven't changed anything other than swapping out TM for Borg. The backups still reside on the Synology (Borg is available on SynoCommunity: https://synocommunity.com/package/borgbackup), and I still backup over WiFi. The Vorta (Mac UI for Borg) client and user experience isn't Apple levels of polished like TM, but I've made it work and I'm happy enough with it.

I'm not sure what causes TM to start considering the volume corrupted, because I believe at one point I switched over to a hardwired connection, but still saw a corrupted volume.

I compared that to Borg, which doesn't flinch if you SIGKILL the process mid-backup, and will basically just pick up from where it left off if you start another one. I saw no reason to continue with TM at all.

I've had this same issue with my Synology. Randomly Time Machine would stop doing backups because the destination was "corrupted".

I've given up on Time Machine over SMB and I'm using Borg + Vorta for my backups. It has the benefit of being readable by any other Linux machine, too.

I agree with your prediction. Sorry, I was unclear in my post, and left that part unsaid. I agree that it will likely just be the big newly released 'base' models that will be scrubbed of NSFW images, but there's really no way to prevent these models from making those kinds of images at all.

It will only take some dedicated individuals, which I know there is no shortage of.

Just to be clear, the child was just an example of someone who could theoretically experience 'cruel' treatment from the current version of stable diffusion. I'm absolutely not recommending people let their children use the model unsupervised. It doesn't have to be a parenting problem, though.

The same could be said (for example) of a random mother trying to get inspiration for a 'my little pony' birthday cake for their child, and being presented with the 'other' kind of image unintentionally, without their consent. I think they would be justifiably upset in that situation.

If we were to imagine someone attempting to put stable diffusion into some future consumer product, I think they would have to be concerned about these kinds of scenarios. Therefore, the scientists are trying to figure out how to accomplish the filtering.

FWIW, I don't think a model could be made that actively prevented people from using their own NSFW training data. The only difference in the future will be that the public models won't be able to do it 'for free' with no modifications needed. You'll have to train your own model, or wait for someone else to train one.

Are these services using textual-inversion? If so, I have to wonder how well they would work on a stable diffusion model that was trained with the filter in place from the start, so that it couldn't generate anything close to the filter.

As it is right now, stable diffusion can generate adult imagery by itself, however it seems like it's been fine-tuned after the fact to try to 'cover up' that fact as much as they could before releasing the model publicly.

I know a person who fine-tuned stable diffusion, and he said it took 2 weeks of 8xA100 80 GB training time, costing him somewhere between $500-$700 (he got a pretty big discount, too, at today's prices for peer GPU rental it would be over $1,000).

Sure, it's peanuts compared to what it must have cost to train stable diffusion from scratch. However, I think most normal people would not consider spending $500 to fine-tune one of these.

Edit: Though I do agree that once this kind of filtering is in place during training, NSFW models will begin to pop up all over the place.

I think the issue they're mainly worried about might be exemplified with a prompt of 'my little pony'. A children's show with quite a lot of adult imagery associated with it on the internet.

A child entering this prompt is probably expecting one thing, but the internet is filled with pictures of another nature. There are possibly more adult 'my little pony' images than screenshots of the show on the internet.

Did the researchers manage to filter out these images before training? Or is the model aware of both 'kinds' of 'my little pony' images? If the researchers aren't sure they got rid of all of the adult content, then there's really no way to guarantee the model isn't about to ruin some oblivious person's day.

So then, do you require people generating images to be intricately familiar with the training dataset? Or do you attempt to prevent any kind of surprise like this by just blocking 'unexpected' interactions like this?

That'll only work for a little while longer (for future named big-public-release models, obviously the cat's out of the bag for the current version of stable diffusion), right up until the point where they incorporate the filter into the training process.

At which point, the end model users get to download will be incapable of producing anything that comes close to triggering the filter, and there will be no way to work around it short of training/fine-tuning your own model, which is prohibitively expensive for 'normal' people, even people with top-of-the-line graphics cards like a 4090.

I think you're right. There's a discount for 'Shows On Sale' members, which you can also apply for (Only $150/month!). The membership application asks how long you've been in the "ticket business" and where you sell your ticket inventory.

If you look into advertising on their site, they describe themselves: "Shows On Sale is a community for experienced ticket brokers across the United States and Canada"

IM and SMS aren't public forums where people you don't know can barge in with their own take on what you just wrote, though. IRC can be, but it would be very difficult to have a grasp on every IRC conversation happening everywhere so you could respond to something you find incredulous.

Unlike Twitter, which incentivizes people carrying on infinite numbers of asynchronous conversations, and encourages people to find them by bringing up 'interesting' ones on the timeline.

That was also Morrowind. I believe they said it happened when the console was running low on memory, they would just reboot when you transition between areas. You would get the dreaded 'long loading screen' which was the console rebooting in disguise.

You could set an image to display while the console rebooted, so they put up a loading screen and rebooted the console. When the console rebooted, the game knew it was in a "loading" screen, and picked up from there.

I didn't mean to imply you couldn't have an n-dimensional array in many programming languages. Just that it's usually not what's done when designing programs. I think many would prefer to make some kind of object to encapsulate the data type (an RGB struct for my example) instead of making arrays of arrays of arrays of (double/float/uint8).

For the literal definition between a mathematical 'tensor' and a (e.g.) PyTorch 'tensor' (which, from reading the other comments here, are not the same thing), I leave that to other commenters. I'm just someone learning PyTorch and sharing my knowledge.

The practical engineering difference between a PyTorch tensor and Python array is that PyTorch comes with tons of math & utility functions that support n-dimensions and are differentiable, whereas the builtin Python arrays and math utilities don't do much, if any, of that.

If it helps you to understand at all, assuming you have a CS background, any time you see the word "tensor" you can replace it with "array" and you'll be 95% of the way to understanding it. Or "matrix" if you have a mathematical background.

Whereas CS arrays tend to be 1 dimensional, and sometimes 2 dimensional, tensors can be as many dimensions as you need. A 256x256 photo with RGB channels would be stored as a [256 x 256 x 3] tensor/array. If you want to store a bunch of them? Add a dimension to store each image. Want rows and columns of images? Make the dimensions [width x height x channels x rows x columns].