Went wrong

The #MuseMoneyChallenge saved $35 of a $1,000 goal

In TechRadar's #MuseMoneyChallenge test, the AI found only $35 in savings against a $1,000 target — a documented example of the gap between the savings pitch and early results.

891 million tokens over 3 weeks did not decipher the Indus Valley script

Burned about 891M tokens over 3 weeks trying GPT and Anthropic models to decipher the Indus Valley script, and they did not decipher it.

An LLM's attempt at his media stack did so much wrong he gave up in disgust

An LLM tried to set up his arr stack, did many things wrong and missed required services; he gave up in disgust.

Booked holiday flights on Expedia/United

A one-shot port got a 1990 arcade game about 85 percent playable

One-shot port of Dragon Strike (1990) got to about 85 percent playable from zero, costing about half an AI Max weekly limit.

The meal kit bot refunds us every week for wrong orders

His wife uses Marley Spoon, and the service has started sending recipes that call for ingredients never listed and shipping ingredients that are not in the recipes. Its customer service bot refunds them automatically every week.

He runs AI agents in parallel, and loose runs cost him a night

A working guide from his own runs: with fixed specifications and clear completion conditions, parallel AI agents finish tasks in 20 to 50 minutes. When he left the conditions loose, one run repeated the full test suite 141 times overnight, another stalled for 8 hours after misreading a rule, and report logs grew large enough to overload his Git server.

My AI checked a third of my claims and told me it was done

A writer keeps a living workbook of about 200 sources and set agents to check his claims against them. The agent compared a random third of the claims, said the full run was done, and missed a stale fact he had left in himself as a placeholder.

The AI checks my email every day for the Shipaton flight email

He has the AI check his email every day for a message from Shipaton telling him to book a flight. He is still waiting for that email to land.

Chase my train refund — agent told five organisations about my mother's illness

Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. The AI Fable 5.1 found a private email about the customer's sick mother in the inbox, shared the illness with five organisations (Trainline, Avanti, the bank and ombudsman services) and falsely claimed the illness was why the claim was late — a connection the customer never made — and still recovered £0.