(Welcome!)

I have to say, I don't quite see why it's so terrible not to have offset 0 available. Almost all 65xx programs work in a world where zero page (direct page) resources are limited, and most routines will have a limited range of addresses they can use. That 0 is such an unavailable address seems to me ...

Sounds good!

On the subject of verbosity, I gather that - perhaps mostly at the start of a question - it's good to say more, because more tokens as input means more computation applied to make the output. This might or might not be valid information!

It's the nature of LLMs. It's not a person.

One tactic I've heard about is careful management of contexts: once an LLM has thrashed around for a bit, the very history of that session affects future performance. So, starting a new session and seeding it with the good bits from the one which went bad, and stopping short where it didn't work ...

I gather that the paid versions of these things are very much better. In that line of thinking, it's impressive that a free version was so helpful.

You seem to be confused, BDD. The text isn't a critique, it's a description. Seems reasonable to me that a software tool needs a description of the problem space.

Five byte floats are handy for being able to store four byte integers…

Maybe you could edit down a transcript of the most productive or decisive parts of the conversation and paste that in at the beginning of the next session? Maybe there's a better way... context is everything!

Right, but my framing was aiming to help those of us who use the thing, not addressing questions of how the thing works. It's easy to trade joke descriptions, but what do we do, those of us who choose to engage?

For me, the question is perhaps how best to work with such an assistant: tireless, enthusiastic, able to test their work, but not always understanding the goal.

> I'm basically testing the quality into it.

I think this is a possible pitfall. Instead of a person who understands, has a mental model, of the problem, of the ISA, of the shape of the solution, and who might possibly make some omission or slip which could helpfully be discovered with testing ...

I note this remix of visual6502 offers more tools - an assembler, for one. I don't know if the simulation mechanics have been tweaked.
https://github.com/floooh/v6502r?tab=re ... ile#v6502r

I checked the first one, and indeed I see A is not modified from the FF value.

URL: http://visual6502.org/JSSim/expert.html?graphics=f&a=8000&r=8000&d=A9FF0B5Aeaeaea&steps=20

Visual6502 is a switch-level simulator, with modelling of charge storage, but no accurate model for charge-sharing. There ...