It didn't end up being very useful - I ran a comparison where I just had a bigger agent do the organization in a more straightforward way, and that had better results.

I did find that Flash 3.6 High was >9x faster than Luna xhigh for this task, and got very similar results, though.

But... if I didn't... I made substantially more money per hour. Partially by being faster, but mostly by being better.

On the surface, it felt like nothing was going on, simple as driving to work, but just having that headspace for intuition to happen made a big difference. Also, probably worth mentioning that I never did production work, only explorative, so perception/intuition was maybe overweighted.

I half suspect that it's true for all of life, though. It's just a lot harder to tell when you don't have the market telling you the value of how you spent your hours each week.

I haven't tried it in a few months, but it went from amazing to unusable really fast.

I'm thinking about inlining an AI chat window directly - I guess I might fire off a prompt to do that right now.

Hard to find a solution that's not worse than the problem itself - same as other weapons, IMO.

So many here get so worried about guns, but don't think twice about how dangerous AI can be.

Would you rather them have:

a) guns

b) psycho-aligned next-gen AI

I miss programming. I wonder if there's any going back, or if it's worth it. I get so much more done, now.

Now, you can use a standard Codex (and maybe Claude) subscription inside of a sidebar, and get a lot of the features you mentioned. It's nice, if you're trying to be more involved with the code, but not as nice for multi-agent stuff.

On the other hand, I did that in pursuit of a goal, and LLM's take me further, faster, toward that goal.