Self-Improvement · What You Can Do Now

It's sharp for ten turns. What about fifty?

This chapter is about letting the Harness evolve itself — sounds far from where you are. But every self-improvement starts with a Harness that can go the distance: it knows when to compress, what must never be dropped, and which conclusions belong on disk. You can set these three rules for your Agent today.

Fifth square on the practice track: you have sprint results. Now train for the marathon.

Know what you want it to do for you

Talks like a human, reliably

Actually gets work done

Better or worse, measurably

Runs long without losing memory

The process is reproducible

See it first · Forgetting is a curve you can draw

When a user says "it got dumber as we talked," what's behind that is a very concrete curve: context usage climbs turn by turn, and once it's full the system can only quietly throw things away. What it throws is usually the earliest messages — the most important rules you laid down at the start.

20 turns of continuous chat: how context usage moves

Context usage 85% compression threshold

Do nothing to manage it, and it hits the threshold on turn 14. Every turn after that quietly drops the earliest messages. What the user feels is "it forgot what I said at the start."

Three rules, three kinds of forgetting

Compression threshold handles "only act when it blows up": compress when usage hits the line. Don't wait for an error.

Never-delete list handles "compressed too hard": the user's original words, the agreed requirements, the safety constraints — once those go into a summary you can't get them back. They must stay pinned in context.

Notes on disk handles "forgetting across sessions": write important conclusions to a file, and read the file first next time you start. That's what this chapter calls "filesystem persistent memory," and it's the starting point of Harness self-improvement. It has to remember what it learned last time before it can improve itself.

Hands-on checklist · Pick one, start it, tick it off

This Chapter's Hands-on Checklist

0 / 3 done

Find the turn it starts forgetting

15 min Everyone

Pull up your longest conversation with an AI. Read it from start to finish. Find the first turn it forgot something you had already told it. Write that number down — that's your Agent's real endurance with no management at all.

What counts as done

You can say "around turn N, it forgot XX." If you can't, your conversations aren't long enough yet. That's a useful conclusion too: your scenario doesn't need compression for now. Don't over-engineer it.

Write your three endurance rules

1 hour Anyone whose Agent runs long tasks

Make the three rules concrete for your scenario: compress when usage hits what percent, which content never enters the compression zone (make a list — don't write vague junk like "important content"), and which conclusions get written to a file. Then paste them into your Agent config or system prompt.

What counts as done

All three have a concrete number or list, and the "never-delete list" at least includes: key constraints from the user's own words, and the requirement definition set in M0.

Run one "write to disk, then read it back"

Half a day Anyone who works across sessions

After the Agent finishes a piece of work, have it write the conclusions into a fixed file (call it a work note). Then close the session, open a brand-new one, and as the first message tell it to read that file and continue. If the new session picks up seamlessly, you've just implemented this chapter's structured-notes pattern — the simplest and most useful form of long-term memory.

What counts as done

In the new session it doesn't ask any "where did we leave off last time" fluff — it continues from the breakpoint. Once you can do this, M4 is standing.

Save the three rules in the Build Log

What M4 needs to record: the forgetting turn, the three rules in full, and where the on-disk notes live. The next square is the last one: turn the whole process into a spec someone else can reproduce.

Fill in M4