🤓 Latest Submissions
.png&w=828&q=75)
Activist OS
Activist OS turns a single community concern into a verified campaign packet: provenance-checked evidence, an evidence-bounded narrative, a volunteer task board, and a full safety audit — before anything is published. Six specialized agents each own one role and exchange structured context through Band: Evidence verifies claims and tags provenance; Campaign turns evidence into a narrative; Safety holds veto power over doxxing, harassment, and unsupported accusations; Outreach drafts public copy; Coordinator builds the task board; Reporter assembles the audit packet. The coordination is visible, not narrated — every one of the eight handoffs renders from the real transport. The product is the governance: Safety can reject a campaign draft, the rejection stays on the record inside the packet, and the system never publishes on its own. Humans hold the send button.
19 Jun 2026
Insult AI
Insult AI is an adversarial reasoning engine for live web data. It uses Bright Data to fetch sources, build a plan, pressure-test claims, expose weak narratives, and ground every burn in receipts. The agent declares its plan before it acts, and receipts are tiered by provenance — fetched fulltext, news search, or company source — so a judge can see what was read versus glimpsed. When the target becomes personal, the system pivots into clinical guardrails: it attacks the pattern, not the person, and switches to safety resources when crisis language appears. PlanGuard vetoes identity-targeting steps before any scrape runs, and a tone selector plus crisis fallback keep the same engine safe across three personas — roast, brief, and clinical — that share one Bright Data pipeline and one safety floor. Live web data. Adversarial reasoning. Receipts. Guardrails. Prove me wrong.
31 May 2026
