Then delete that data and let the user start over. How come Apple gets to hold iTunes purchases (apps, movies etc.) and somebody's email address hostage just because they also happen to store some end-to-end encrypted data on the same cloud account?
Just imagine Google letting people "brick" their accounts because they have a password protected PDF in their Google Drive they don't remember the password for...
And that's to say nothing about the not end-to-end encrypted data, which is still the default for most things in iCloud accounts (without ADP enabled).
Read the article, that's not true by default, the only way you get that level of cryptographic protection is if you enable "Advanced Data Protection". None of the people in the article did that, all of them can trivially prove they are who they say they are via government documents, Apple could decrypt their data and return it, but Apple is refusing to do so.
It's simply not Apple's responsibility. Person's data, their responsibility. Any other way and people lose trust in Apple which BTW they protect it by any means. Trust.
Instead of wanting something impossible, accept the reality.
You're 100% correct, most models these days know most programming languages and will quickly learn the syntax of more niche languages.
For users that end up benefitting from rules, it's typically because of encoding "personal knowledge" or "preferences". When building small side projects from scratch, this typically matters much less: you probably want it to "just work" using the canonical tech stack. Pretty quickly though projects end up with a lot of implicit knowledge and idiosyncratic practices that are great candidates for custom rules!
I guess you would be paying for pushing all of these tokens to the LLM. Also, too much irrelevant context can "confuse" the model about the task at hand
Check out NVIDIAs latest releases. Paying for tokens is going to be a history in about 6 months. You run the model on your laptop.
Maybe you're right about the confusion...but given the velocity, that's going to be fixed also.
All the knowledge about the field of programming is digitized, one could argue that having a model that digested all that information in a right way, is better than separate.
Absolutely +1 to the progress of local models! We hope Continue is and continues to be a great place to use them. Tons of blocks in the Ollama page for example that can be used: https://hub.continue.dev/ollama
I kinda concur and i think there is also a business needs mismatch. OP's approach requires a very holistic and integrated view on things, a lot of experience and academic knowledge. It would probably be a better approach, but it requires upping the requirements who can be a SE and how its taught, software might not be a commodity in this world.
The beauty of today's "cloud native" approach is that everything is basically just a layer on top of another layer and you can be completely ignorant of everything below and make stuff that even if inefficient, works. We can churn out a lot of people and yes, they will make crap, but crap that satisfies the needs of the business and creates real or perceived value for it. Arguments can be made that long-term its a loss since the codebase will rot faster, but everybody responsible will be long gone and don't care, they don't have incentives for this.
A week ago I interviewed a guy who delivered multiple projects over his 10 year career in large companies and he had no idea what's multithreading or concurrency. The academic in me weeps, but the manager/engineer in me was impressed that you can be so completely ignorant of all lower layers, but still produce said value. Would it be possible in the noted holistic approach ?
I have reality -> that's the thing i'm working on, which happens to be a bunch of very hard problems which I need resolved as that's for a client. Then I have a dream -> that's the thing I want to do before I expire. And most theory is for the dreams, but the 'easier' project already needs a lot of research & effort.
