It’s not as good, but running small LLMs locally can work. I’ve been messing around with ollama, which makes it drop dead simple to try out different models locally.
You won’t be running any model as powerful as ChatGPT - but for quick “stack overflow replacement” style of questions I find it’s usually good enough.
And before you write off the idea of local models completely, some recent studies indicate that our current models could be made orders of magnitude smaller for the same level of capability. Think Moore’s law but for shrinking the required connections within a model. I do believe we’ll be able to run GPT3.5-level models on consumer grade hardware in the very near future. (Of course, by then GPT-7 may be running the world but we live in hope).
I’m aware. I looked into it regarding your source code being used to train their ML. I looked over the FAQ and got the “Your code is your own.” vibe. Sadly it does point to their standard Privacy statement that could change anytime and allow them to do what they want.
No. We follow responsible practices in accordance with our Privacy Statement to ensure that your code snippets will not be used as suggested code for other users of GitHub Copilot.
As a bad Python scripter, I’m stuck using Microsoft’s AI because there isn’t a privacy-focused alternative anywhere near as good.
Don’t overuse AI, there is plenty of resources on the web and at least you can practice reading docs. Use Phind. https://www.phind.com/privacy
It’s not as good, but running small LLMs locally can work. I’ve been messing around with ollama, which makes it drop dead simple to try out different models locally.
You won’t be running any model as powerful as ChatGPT - but for quick “stack overflow replacement” style of questions I find it’s usually good enough.
And before you write off the idea of local models completely, some recent studies indicate that our current models could be made orders of magnitude smaller for the same level of capability. Think Moore’s law but for shrinking the required connections within a model. I do believe we’ll be able to run GPT3.5-level models on consumer grade hardware in the very near future. (Of course, by then GPT-7 may be running the world but we live in hope).
SkyGPT
GPT4all is another good local one. Runs on CPU but you can use GPU acceleration. Some models even run on my crappy dual core laptop.
Check out github copilot
Not free. But it’s cheap paid and supposedly privatey focused.
“If you’re not paying for a product, you are the product.” Shame usually it’s both!
Github copilot pirates other peoples code. Legally that’s hard to pursue buts its enough to make me dislike them.
Oh their model is 100% taken from public repositories. I doubt they bothered to even filter it out to open source/fair use code.
My issue here is AI isn’t going to replace my job, but an engineer who uses AI as a tool would replace me…
It’s still Microsoft. Here’s what they say about privacy anyway:
Individual
Business
I’m aware. I looked into it regarding your source code being used to train their ML. I looked over the FAQ and got the “Your code is your own.” vibe. Sadly it does point to their standard Privacy statement that could change anytime and allow them to do what they want.