Blog · Concept
Self-evolving software: miracle or chaos?
August 14, 2026 · dshbase
DeepSeek Harness has been called both the prototype of self-evolving software and a recipe for even more chaos. The split comes down to one feature: an agent that can modify its own running capabilities. Here's what that actually means — and why the cautionary tales matter.
What "self-evolving" actually means in DSH
It's not science fiction. In Create mode, the agent can inspect its own running Cordis environment, experiment with plugins in memory, and — critically — create a plugin and hot-attach it to the running flow. The "make your own wrench" metaphor: the agent notices it has no wrench, forges one, attaches it to its hand, and keeps working.
This works because Cordis guarantees two properties: temporal composability (unloading a plugin fully undoes its side effects) and spatial composability (dependencies re-resolve as siblings change). Without those, hot-swapping your own code mid-run would corrupt state.
The cautionary tale: OpenClaw
The skepticism isn't hypothetical. OpenClaw, an earlier agent that promised a similar "everything is modular" vision, ran into exactly the chaos critics predict — a reminder that self-modification without safety rails produces unmaintainable state, not evolution. The difference DSH argues for is Cordis's composability guarantees, but that's a claim that still needs proving at scale.
A practical guide to self-evolution
If you want to use this carefully, treat it as a controlled experiment, not free rein:
- Scope it down — start with read-only presets (e.g. "read code, never modify files") before anything that writes.
- Use the trajectory log — every tool call and permission change is an event; review what the agent actually did to itself.
- One change at a time — have the agent add a single plugin, verify, then continue, rather than letting it rewrite everything at once.
- Keep a restore path — profiles and presets mean you can always revert to a known-good config.
The honest take
Self-evolving software is neither a miracle nor automatically chaos — it's a capability with a failure mode. The miracle framing oversells it; the chaos framing underestimates Cordis's safeguards. The truth will show up in whether real teams can use it without losing control. For now, the practical path is scoped, logged, reversible self-modification.
Related: session log observability · the Create mode.