This is the one I use, both for myself and the kids. How you practice will become how you play, so it's important to make sure you have good form and technique.
There's another, similar saying used in fighting-related disciplines: train how you fight.
Same idea. You're building muscle memory and technique, so make sure your training/practicing matches how you'd do it in a performance (or fight). It's one less thing to have to think about when you're under stress.
Just keep in mind if you're providing value the scrapers will soon appear to claim it for themselves... look at what Craigslist does to protect their data though you want all traffic as you get off the ground.
GHCP also has magical rate limits that hit users that slam multi-agent workflows or other crazy request burners.
Mind you, I think GHCP is a great service at an excellent price, but the hardcore vibe coders complain about the rate limits that I've never personally experienced using the CLI.
That's weird, because every time I see someone even talking positively about Claude Code they always seem to mention they're hitting their 5 hour limits in 2-3 hours all the time, they're hitting their overall limits all the time, and so on.
Meanwhile I can't even seem to spend my $20 Cursor Composer 2 tokens using their agent. I've been doing useless shit just to see how much usage I can cram in there and it'd probably take 10 hours of vibecoding like a loser every day to hit the limits at this point.
With that said I'm not going to pay for something that doesn't allow me to use whatever I want to use (in terms of harness, etc.), so both Anthropic (who were already disqualified because of their ridiculous limits) and Cursor is out (AFAIK you can't an agent other than their `agent` binary without some ridiculous hack like proxying all of the calls through `agent`.
I can't imagine all of the providers pretending their agents are real value going forward, but even if they do there's still stuff like OpenRouter which doesn't give a shit, may as well use something like that.
I haven't done the exhaustive research but props in advance for being the only person shouting in caps on HN. Definitely one way to proclaim one's not AI-ness without forced spelling errors.
I think it's that the biggies are focused on big budget AAA titles that they can sell for $70 or monetize as a FOMO live service, their distinguishing factor compared to indie games is high production values, and they don't feel like they have enough of an advantage in this space, or that they can get enough revenue to justify the huge expenditure of a AAA game.
Basically the same reason many other genres (e.g. roguelites) are dominated by little indie studios.
Plus the studios that have become AAA did it because they implemented interesting ideas, limited by their size constraints. The they get scale and lose the size constraints that caused the to go after interesting ideas.
The real successor to an old AAA series is the new series made by people who played it as kids.
The parent pointed out that there are financially successful games targeted at women that AAA studios won't make. Corporations are made up of people who have their own biases. I know so many people who would kill for a more modern Sims game.
They have one. It's just that "modern" for "AAA" games means it's a microtransaction mall and advertising delivery vehicle. Though admittedly as far as I know it doesn't have gambling mechanics yet, so could be further modernized.
I'm sure there's a huge incentive in these studios to sell games to women, but women (mostly) aren't buying them. That is despite overwhelming evidence that women play games they do like, and play them a lot.
So by greedy capitalist standards, these companies are falling short of what they want to do.
reply