Not to do a "The Amiga was ahead of its time" thing but as a reminder, 68000 has a flat 24-bit address.

A model like GLM-5.2 being available as GGUF, usable through llama.cpp/Ollama/vLLM/SGLang/LM Studio, and wrapped for local agent workflows changes the category. It stops being an impressive open model exists and starts becoming this is something a small team can actually put into its development stack.

For instance, company buys an RX6000 setup for say $15k total. They could use this for handling data heavy sifting that would otherwise be a lot of Claude tokens.

It doesn't need to be as good as frontier-best. Just good enough.

I could see a business of people packaging this and handing it to companies who want Help Desk bots without any extra setup.

I've had to rip out a lot of pretty terrible code made by engineers who have tried this.

I don't disagree that eventually, "loops" when combined with unlimited tokens and amazing models in the hands of people who know how to set them up right will be amazing. But for the typical Claude Code user, it's disaster.

The problem is not that loops write bad code once. Humans do that too. The problem is that loops apply local pressure repeatedly: add a fallback, add a guard, special-case the failing input, quiet the exception, satisfy the test. Over time that selects for code that is more survivable in the short term but less intelligible in the long term.

This past year we were porting Elemental (PC game) to 64-bit so it's pretty old code. There are a gazillion different string types in it (sprintf and beyond).

Now, for me, it was really about how well it worked on big existing human made code bases. I was working on some new screens in GalCiv IV and if you've ever had to make screens for games, it is incredibly tedious, low brain work. But GPT 5.5 and Opus 4.8 would just struggle with these over and over again and this is C++ work with limited hotloading so it's a slow process. Fable nailed these screens fast.

The random reservation order takes the scalping issue out of the fulfillment part and into allocation making it a lot harder on the scalper.