Probably an unpopular take, but this is why copyleft and agentic coding should be considered aligned in principle. Both can subvert closed source lock in.

It's also good for user privacy. I suppose it can accelerate privacy invasions that software makes, but the thing with software and services is you generally get to choose which ones you use.

1. AI coding gives privacy-focused software creators more ability to create great UX allowing for them to be more serious alternatives to privacy-invasive software and services.

For example, I've tried Matrix many times and I've never liked the UX, but recently I started using Fluxer, an open source discord alternative, and it has excellent UX.

2. AI makes software more secure. You cannot have privacy without security so AI improving security is good for our privacy. Frontier AI does not write more insecure code than human coders so it's overall great for privacy.

3. AI accelerates reverse engineering of closed source software. This can help discover spying e.g. the LG TV spying news recently, and can also make closed source software work for the user instead of against.

I recently made 4 tweaks to apps to make them more privacy focused:

I added self-hosted E2EE to a closed source to-do app and made an Android app.

I patched a closed source workout app to make it work completely offline, unlock premium, and remove unnecessary permissions. The app is now 600 MB because of videos! I also did this with a habits app. Before, both these apps connected to 40+ domains for tracking and their services, now they don't have the network permission.