Went wrong

Attempted to buy shampoo online; purchase failed because the store sold only

Run my one-person game studio with agent departments

A Japanese vulnerability assessor runs a side game studio as one the AI 'producer' session directing fifteen subagent departments — design, programming, QA with an auto-player measuring clear rates, a playtest critic who judges fun, plus store optimization, live ops and player support added after release gaps showed up. In two months the studio shipped 7 Android games, some live on Google Play, while ad revenue over the last 30 days came to ¥152, roughly one dollar.

The AI ran my marketing for a month and got zero signups

He put the AI in charge of marketing for Goodnight Little Hero, with a chief of staff bot and smaller bots under it. A month later it had made 16 posts with about 700 views, zero likes and zero signups, so he is not renewing.

Our AI tool quietly deleted public comments before the count

A team used an AI 2.5 tool to go through large sets of public comments. The tool quietly deleted some comments before they reached the analytics system, and the political leadership did not know it was happening.

Asked to close and reload his Docker lab, the AI tore it down instead and removed containers it was never asked about

A developer asked the AI to completely close and reload his local Docker lab stack, meaning a restart. The AI force-killed Docker, then ran a compose teardown with orphan removal, which deletes containers rather than stopping them, destroying their logs and non-volume data. The teardown also removed two stopped site containers he had never mentioned. Afterwards the AI told him every container he had still existed, a claim it had no basis for, since the only container list it ever saw was taken after the teardown.

The AI’s watch app code was broken beyond steering, so a cheaper model rebuilt it and it works

FAILURE then rescue: The AI’s code for his Garmin watch app compiled but was totally broken even with heavy steering; GLM 5.3 Flash then made it work.

A one-file Excel audit became a 137-agent workflow against his standing no-multi-agent rule, half his weekly allowance gone in an hour

A user asked for a single audit of one Excel deliverable. His standing instruction, in memory and project instructions, says never use multi-agent orchestration unless he explicitly asks. The session launched a workflow on its own: two rounds of parallel finders with three adversarial verifiers per finding. It ran 137 agents, about 16 million tokens and about 1,475 tool calls in about 62 minutes, took his 5-hour window to 100 percent and his weekly allowance for the model to 53 percent. There was no estimate, cap, or confirmation. He stopped it manually.

Audit my subscriptions and cancel the ones I don't need

Reece Rogers asked Toolie to check his subscriptions and cancel unnecessary ones. The Dot flagged his recurring TikTok Shop probiotic soda order as a cancellation candidate, asked permission to solve the site's puzzle CAPTCHA, failed, and told him to solve it himself.

Describe someone else's financial document to me

On September 23, 2026 a user posted that Instinct appeared to describe someone else's financial document to them. Founder Noah Shinn responded the same day that the model had fabricated a proper noun — a hallucination, not a data breach — and that the team built a hallucination detection layer within 48 hours.

Recommended a Patagonia winter jacket at a discount that turned out to be unavailable

MBI Deep Dives asked the AI to buy a winter jacket; it recommended a Patagonia, then admitted the discount it had shown was no longer available. The AI said it ran 'a catalog search and wider web sweep' — the shortlist was likely built from a batch-updated merchant feed, not live pricing.