You’re viewing the 2026-08-10 issue, not the current issue. Go to the current issue: 2026-08-14

Featured in Domain Arrivals · 2026-08-10

Terrible Agents Keeps an Honest List of AI Failure Modes

terribleagents.com ↗ · AI Table · score 86.0
Open: public page gives enough substance to understand the site $Paid: pricing, booking, ecommerce, subscription, or paid access is visible ADAds: visible ad load or ad-supported content Pretty: notable design, copy, craft, or presentation Pro: polished, finished-feeling, serious, or operationally mature Niche: specific audience, workflow, or unusually focused use case Human: personal, local, community, civic, handmade, or real-person signal !Suspicious: scammy, spammy, trust theater, finance fog, or credibility concern

A public catalogue of eight things AI agents still get wrong, paired with the safeguards used to contain each failure.

Why it surfaced

This is an unusually candid AI page: its agents' problems include hallucinated facts, unattended spending, spammy outreach, fake-human behavior, stale information, and runaway loops. The proposed fixes are concrete—citations, spending caps, human approval, disclosure, written memory, and kill-switches—giving the site both a memorable voice and a useful argument about trust.

Ham Is Specifically Discouraged

August 10’s newborn domains include a mock cryptid council that specifically discourages ham, a vintage phone collecting messages for Twyla’s 70th, a 4.5-meter dish measuring Galactic hydrogen at 1420 MHz, and an open index that found 530 sites permitting GPTBot in robots.txt while refusing it at the server.

This is one of 1,000 discoveries in the 2026-08-10 Domain Arrivals issue.