00 / Masthead
Tag
3 entries on this thread.
The technique behind viral AI agent loops: treat context like managed memory. State lives in files, not conversation. Progress persists. Failures evaporate.
Read entryStandard Ralph gates on tests passing. My version adds an adversarial intelligence that must explicitly sign off before progress is allowed.
Read entryI was losing 40k tokens on startup. So I built Flow, a plugin that uses command stubs, progressive disclosure, and adversarial review loops.
Read entry