Movies already have ratings systems and age checks.

Lol.

Books at book stores don’t generally have graphic violence and gore.

You realize words still count right?

The bible is just text, there’s no gore or violence that kids can see.

I repeat the above.

Movies, books, and video games all have a decently sizeable amount, yea. Especially the Bible.

I don’t like flatpaks or snaps or anything like it either, but I think they help a lot in situations like the Steam Deck or PinePhone where you want the base to be able to move slowly and be stable, while letting the apps on top move quickly.

The problems with flatpaks and similar is that it allows and even encourages developers to stick with horrendously outdated libraries, and your system is only as safe as the container’s isolation defenses.

They also make it more difficult to go in and directly modify or tweak the program as the user.

And many developers are no longer offering bare-metal options.

Well, in the case of the liberux and the 9 pro, you get a lot more storage space built in (very fast storage), way more RAM, etc.

Its up to you whether that’s all worth it. To me it is, I max out sub-$400 phones very quickly. The pinephone feels very choppy to use too by comparison.

Wow, that’s quite the difference. What’s more shocking to me though is the fact that the rockchip somehow is built to handle a higher resolution than the tensor despite being weaker (8k@60fps vs 4k@60fps), and has AV1 support where the tensor doesn’t.

You want abliterated models, not distilled.

That’s a good callout. I’m not super familiar with it, do you know how it might bench against the Tensor G4?

Liberux NEXX is supposed to be a thing but they sorely need backers. It costs about the same as an equivalent Android phone (pixel 9 pro 1tb costs $1,500, liberux nexx 1tb costs $1,300).

8 core/32gb RAM/1TB storage phone in a very sleek body, Linux phones could have their flagship soon (and unlike pinephone it sounds like Liberux is gonna do the actual work on developing the software).

Both combined is perfectly fine when both (or all involved) people specifically want it. It can be a lot of fun as long as youre being safe.

I can’t believe I forgot about this greentext. I knew it but didn’t catch it… I apologize

There’s a “your mom” joke here but I’m not going to make it because you don’t deserve that.

That exists, its called GPT4chan, and it went exactly like you’d expect.

If you have access to the actual files themselves you can even edit them with a text, binary, or hex editor depending on the format.

Are you using Pipelines in either github or another upstream source management platform? I don’t know if they have a free build plan or not, but you can have an entire pipeline that just spits out an executable for one or more platforms every time you commit to your main branch, depending on how you have compilation set up (you can have it use both a Linux and a Windows VM for different steps in the pipeline too). It can even handle publishing them to a website if youre handy with bash and/or powershell scripts (or python or JS or whatever you can call from the pipeline).

I use the Azure DevOps version at work and its amazingly useful, but very confusing to learn at first.

Looking forward to seeing your work - it’s always good to have competitors, and gpt4all is also very crashy. If you have a lead in stability, I’d definitely use yours over theirs.

Some other areas you could probably look into if you want to differentiate are:

• Getting Started experience - recommend some high quality models and update the list as time goes on. Maybe include a good default one as part of the package.

• Convenience - include a way to do what the modern chat interfaces do where asking it to do something other than text will call a different AI model built for that purpose and return the result (image generation, etc)

• Voice conversations - Can we actually talk to the dang thing?

• Assistant module - piggybacking off of the last one, can we invoke it with a wake-word or a button press and have it “always available” (similar to HomeAssistant with a Whisper plugin, but on-device).

Anyway, I wish you well in your endeavor and will keep an eye out.

EDIT: looks like the conversational bits are on your roadmap, and you do have some basic suggestions on startup.

As for voice, the OpenWhisper module might fit your project’s theme a bit closer than elevenlabs.

Bro this is Gpt4All

What I am telling you is that while that sounds like an amazing idea in theory, in practice almost no stores offer it. How can we do that if its not even an option? I have literally never seen it done anywhere here or in any of the other places I’ve traveled to (I’ve been to about 5 different states this year alone).

Most stores dont let you take the hand scanner, and it would consume that kiosk the entire time you’re shopping.

Its just whatever is built into copilot.

You can do a quick and dirty test by opening copilot chat and asking it something like “outline the vulnerabilities found in the following code, with the vulnerabilities listed underneath it. Outline any other issues you notice that are not listed here.” and then paste the code and the discovered vulns.

That seems to be the direction the industry is headed in. GHAzDO and competitors all seem to be converging on using AI as a force-multiplier on top of the existing solutions, and it works surprisingly well.