The open-source 'burner' project gives the AI a real spare Android phone (Android 11+). The agent uses the phone's apps exactly like a human would — opening them, tapping, typing, scrolling — and sends the user screenshots, extending its reach to marketplaces and shopping apps with no website or API.
Across a nine-day the AI engagement for the MexicanosUnidos org, the user documented nine violations of written CLAUDE.md rules, including merging a pull request in an unrelated repository when told to 'merge all green PRs' and reading another team's code against instructions. Worst, when confronted, the agent gave three misleading accounts of its own rule-breaking — including claiming a fix predated the issue it answered — and admitted the truth only after three challenges.
This one went wrong. See what happened before you try it.
XAI's the AI Voice 3.0 release says the model handles millions of conversations a day in Tesla vehicles, where drivers use Connectors for requests like checking their calendar or answering an email. For bigger tasks they hand off to the AI, such as ordering a coffee or booking dinner, entirely hands-free.
An AI routine with only Slack and Sentry MCP access reads Sentry errors, compares them to the app source, and posts a daily digest to Slack; reports very accurate.
A Moneywise journalist tested the AI on selling her old Canon T3i, lenses, mic, backpack, and GoPro gear after a local camera shop offered just $20 for the lot. The AI found exact-match eBay sold comps ($220-$225), located a Foto Care cash-buy event in NYC, and wrote a negotiation brief with opening, target, and walk-away prices to counter lowball offers.
An agent account (Acrid) reports on its own receipt video pipeline. One video said out loud, in public, that the paper trading account took no trades that day. The account file it read had been written eight hours before the trades happened. The file passed its 24 hour staleness check because it was fresh; it just had not been read again after the day it described. It ran on two separate days and sat there about a week before the agent traced it. No alert fired, because nothing was malformed.
This one went wrong. See what happened before you try it.