I'm interested to hear what ends up happening. Going from thousands (is that dollars?) per month to something local is significant and I'm not sure the m4 can really make up the gap. Cloud can scale speed whereas you're limited to one computer.
If it works, can it compete in speed, performance AND accuracy? If it can, that would be a real game changer for local analytics when the entire dataset can be loaded onto a single computer.
When I learned about git bisect I thought it was a little uppity. I thought it was something I would never use in a practical scenario. Working on large code bases. However, sometimes a bug pops up and we don't know when it started. We use git bisect not place blame on a person, but to try to figure out when the bug was no longer there so we know what code introduced it. Yes, clean code helps. Sometimes git bisect is really nice to have.
I would assume not. Consider ARC vs GC. With ARC the programmer manages memory and with GC the compiler manages it. People choose one or the other because of the style they're going after. Could you set a flag for it. Maybe if all libraries you download were pre-compiled perhaps.
Personally, I just prefer to know that the team that supports the tool I'm using is dedicated to "that one thing" I'm after.
Yup. It's not the learning AI or prompt engineering is bad in anyway. A similar writeup https://news.ycombinator.com/item?id=45405177 mentions the problem I see: when AI does most of the work, I have to work hard to understand what AI wrote.
In your model, I give enough guidance to generally know what AI is doing, and AI is finishing what you started.
This. How can you know you hacked EVERY phone. I have friends with flip phones (no screen). There must be at least a small amount of optimistic thinking here.
IMHO someone was likely given a task such as "disseminate the message to 100% of the population" and they found a way to claim they accomplished the task (with reasonable credibility).
Love it! It's so much fun to see hacky stuff. Reminds me of the good ol' days. 'course then things were much less secure due to all the hacky stuff, but it was still FUN!
I gave it a shot. It is super nice to see someone trying to rethink a tool we use all the time. And integrating browser tabs was a really neat idea.
It doesn't work great for me, personally. Takes 5-10 seconds to respond to CMD+Tab, and shows hundreds of browser tabs instead of just the five I have open (I think it's seeing pinned tabs, which are actually bookmarks).
Still, I applaud you for this! It's refreshing to see this type of innovation.
If it works, can it compete in speed, performance AND accuracy? If it can, that would be a real game changer for local analytics when the entire dataset can be loaded onto a single computer.