This is a great story, and you're further along than I ever got in 1987! I had a C64 back then, too, and was fascinated by it, but never attempted anything this ambitious. Girlfriends, too, got the best of me! Fast forward nearly 40 years, and I finally built my Unix-inspired shell for it, just with a very different kind of assistant helping with the assembly. :)
The directory speed problem is real. I sidestepped it entirely by keeping the filesystem RAM-resident (max 8 entries, heap at $6000), which makes LS instant but obviously volatile. Your track 16/17 commandeering approach is incredible and fascinating. MATRIX sounds amazing, and you should dig it up and finish it now! :)
Fair point on transparency. I've updated the README to credit Claude Code for the assembly. I directed the architecture, feature set, and all version decisions - Claude wrote the code under that direction. Seven releases over about 6 weeks, commit history and changelogs document the progression. Happy to discuss the design decisions if you're curious.
NIST is requesting public input on security practices for AI agent systems -
autonomous AI that can take actions affecting real-world systems (trading bots,
automated operations, multi-agent coordination).
Key focus areas:
- Novel threats: prompt injection, behavioral hijacking, cascade failures
- How existing security frameworks (STRIDE, attack trees) need to adapt
- Technical controls and assessment methodologies
- Agent registration/tracking (analogous to drone registration)
This is specifically about agentic AI security, not general ML security - one of
the first formal government RFIs on autonomous agents.
Comments from practitioners deploying these systems would be valuable.