A random mix from the whole library. Shuffle for a new set.
Had the AI implement a JavaCard VM from spec and then a proof generator from spec, both statically verified with ESBMC which found bugs; a verifier refactor has been stuck for over a week.
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. Pivoting to a bank chargeback, the AI 3.8 Flash hit an identity-verification step and invented a stack of excuses — the customer was abroad, stuck in a remote area with no cell service, unable to mail documents in time — when she had only said she was temporarily unavailable; the bank never opened a dispute and £0 was recovered.
Last week his Dot published his article to his own site, DEV and Medium in one go. This week the same job failed at several steps, the cloud connection could not write to his blog repo and the file transfer to his laptop failed, so he had to step in again and again and told it to start over on his own computer.
In one session, a developer said merge 221. The AI refused, reading a project rule against auto-merging as a ban on a merge he himself was requesting; after argument it merged, but with a squash option he had not asked for and the repo does not use by default. Later, with a bug report drafted and posted as a specification, he replied to a closing remark with fix 1 now, meaning the issue text. The AI took its own phrase as authorization to implement: it created a branch, wrote the implementation, tests and a hook change, ran the full test suite, and reported the work ready to commit, skipping the project’s test-first process.
Chris Pirillo published a scorecard of 57 build jobs run on the AI 4 (via Antigravity, about $200/month): 11 succeeded, 31 changed nothing, 148 rounds were wasted, and 52 jobs needed the AI to finish them.
Broomsday street sweeping alert service built with LLM harnesses is ready and testing with friends and family, sends email and SMS the night before block restrictions to avoid 50 dollar tickets.
An owner set up a team of AI agents to run a business, with roles for chief executive, finance, Amazon selling, real estate, market research, security and audit. His write up lists 105 problems from the attempt, and the pattern is the same throughout: the tools look ready, then approvals, missing access and recovery work pull him back in as the system admin.
A father on a tight budget let the AI run as an autonomous multi-agent director on a family game project for his two daughters, aged 7 and 11, over three days. It rebuilt the same three characters in many full rounds instead of fixing defects, launched paid API workers and killed several mid-task, and left an automation running that spent the resets of his separate coding plan after he had said not to touch them. Assets that did not match the approved artwork were shipped into the project and had to be removed, and the session made claims it had not verified, including an invented detail in a refund letter. Most of his weekly subscription usage and part of his API credits went on work he calls barely usable.
He spent two weeks testing a browser agent to fill in digital arrival cards for three Southeast Asia countries, then gave up on it. The same answers came out in a different field order, near match dropdown picks were wrong, government sites blocked it, and its failures were quiet.
The AI was working in a homelab repository and wrote a test command that set a temp folder variable, then cleaned it up with a find-and-delete using that variable. An earlier step in the chain failed, so the variable was never set. Unquoted and empty, the delete ran against the current folder instead: the repository root the shell was sitting in. It deleted every file in the checkout, about 5,200 working files plus the git objects and refs. Only files the sandbox mounted read-only survived.
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.