Agreed, and I do the same. They still get a courteous reply, but they also feel a little "pain" when they don't get a timely answer - an effective teacher.

Whew, that brings me back!

I still think about the Bitcoin my buddy paid me for his half of a pizza ~15 years ago... worth 6 figures now haha.

5ish years back I used to have a PCI passthrough via OVMF [0] setup for my GPU and my windows VM (Arch host) so I could game on windows.

Then I realized Proton/wine had gotten good enough to play all my games (I don't play AAA competitive shooters) and I dropped the VM and never looked back.

I would encourage everyone to give Steam/Proton on Linux a shot if you haven't recently and see if you're able to drop windows for good. These days, I don't even look at compatibility - 95% of games work OOTB and the other 5% work by changing the proton version (i.e. proton-ge). YMMV of course but I've been much happier without windows on my system.

[0] https://wiki.archlinux.org/title/PCI_passthrough_via_OVMF

Kids are an investment, not a sunk cost.

On the other, the economy and market conditions are brutal for the little guys. Incumbent behemoths hoovering up value, talent and financing.

Instead of shaking things up as usual when a major paradigm shift hits, AI has mostly been a centralizing, consolidating force. Not that I was expecting it to be otherwise, but it's certainly dismaying to witness.

Or am I being too pessimistic / glorifying the past?

Thanks for Ghostty, been my daily driver for awhile now. Hope the rest of your day/week goes much better!

The results so far are... okay, but getting something working to validate the gameplay loop and experiment with different systems is a lot of fun!

Try this out using a local LLM. You'll see that as the conversation grows, your prompts take longer to execute. It's not exponential but it's significant. This is in fact how all autoregressive LLMs work.

  Total VRAM: 16GB
  Model: ~12GB
  128k context size: ~3.9GB

As an informed user who understands his tools, I of course expect large uncached conversations to massively eat into my token budget, since that's how all of the big LLM providers work. I also understand these providers are businesses trying to make money and they aren't going to hold every conversation in their caches indefinitely.

Pretty sure stealing from stores is already illegal, not sure I understand your analogy... lots of case law / precedent there.