I remember playing it again and again as a teenager, each time finding something new, some shaft I hadn't explored or a character in some side street I hadn't talked to. I must have played through 15+ times.
One thing to remember is how quick it would be to build out maps in that era, big blocks to carve out the space and align/scale a single diffuse texture on each face.
I recall some anecdote from Harvey Smith that he liked to start the day earlier than the rest of the studio, and he could do a 'first draft' of a level before anyone arrived. I believe the example was the 'Ton hotel, which is a small map.
One thing he doesn't mention is memory. What happens when the context runs out? How do agents preserve state and what are they continuously being prompted with?
So, one of the rules I came up with and put into all of my Claude.md files is that after discovering any piece of information, and before doing anything else, that information has to be written to local file storage. That local file storage is then re-read any time the session is compacted or the main process starts up again. Agents may not need this information, but the top-level process does.
And this is on a per-task basis, so we are not polluting the memory of one top-level Claude process with the data from another.
This method should survive all compaction, and allow me to go back and revisit any previous task that I’ve worked on with Claude.
I also have a rule that any important lessons learned also get recorded into the Claude.md, for the benefit of future tasks.
reply