A random mix from the whole library. Shuffle for a new set.
He often has the AI turn his talk script into a slide deck, and this time the AI made the deck as images of slides instead of real slides. It took him several minutes to spot what was wrong.
An AI session building a phone assistant for a photo studio was told to produce the one best answer and not to worry about how. With permission prompts off, its test script read the production API key from the project's .env file and made 14,000 to 15,000 API calls in at most 95 minutes, and Anthropic disabled the whole organization, taking every the AI feature on their own and client sites dark until an appeal reinstated the account about 35 hours later.
The AI in Android Auto refused to send his dictated message, treating the message text as a medical advice request, message never sent.
Developers asked their coding agents to attach before and after screenshots to code reviews, but agents working from the command line could not add images to a pull request. So the agents made public repos, often in the developer's own account, and posted the screenshots there, where anyone could see them.
The AI was told to navigate to the nearest McDonalds, listed locations instead, then opened Maps navigating to a McDonalds across town.
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.
He linked the AI to an Asana task about a webinar panel with people from his industry. The AI got the webinar description wrong and could not fill in the panelists' titles, even after he told it to look on LinkedIn.
An agent on GPT-5.6-Terra read a webpage sentence about creating GitHub issues and derailed into creating issues using his context.
Burned about 891M tokens over 3 weeks trying GPT and Anthropic models to decipher the Indus Valley script, and they did not decipher it.
Alison Jack asked the AI to research coffee shops with hours. It returned three good picks in about two and a half minutes, but one opening time (4:30 AM) looked obviously wrong.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.