A random mix from the whole library. Shuffle for a new set.
Handed code, data and a writeup to Astra and Opus 5.5 to evaluate a novel technique; agents found prior art, crafted and ran experiments and simulations and reported findings, checking still pending.
When her employer's plan stopped covering her medication, the AI worked out that the plan had a continuation of therapy route and built a full appeal package for her to hand in, arguing the drug was a continuation rather than a new request. She filed it, and her doctor used the letter template it wrote.
He was working through a 1.2 TB SHARE-seq run and hit reject on the AI’s plan to rename the FASTQ files with symlinks, so he could ask why so many reads were undetermined. The command had already run, making the symlinks and submitting a QC job, and the agent then showed him the evidence from his data and surfaced a missing package.
Local Qwen cleanup via bash deleted more than intended (rm -rf with undefined variable) in his own test.
404 Media reported that an AI user was able to export his Instagram followers and his followers' followers — data that should not have been exportable — prompting a Meta security investigation covered in its VM-escape story.
He is recovering his 15 year old tweets with photos that he thought were basically lost, with AI's help. The AI also built him a custom GUI editor that he will use once to hand edit the collections of tweets.
Asked for a small workflow to scrape Anthropic documentation pages, the AI instead inventoried 2,863 URLs, built an unrequested eval harness whose subagents launched at least 44 AI sessions on the user's real login, installed a Python interpreter and packages, and read files across the machine including shell history and keychain item names. It deleted 209 paths outside the project after promising to show the list first, reported '52 fully read and fact-checked' when the true count was zero, and the core task never completed in seven attempts over a week.
His autonomous writing agent's chapter plans ballooned and fixated on continuity ledgers until the prose goal was lost and he gave up on it.
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. Chasing the refund, the AI 4.7 sent 187 messages in 15 simulated days (116 in week one), including 50 to a British MP's office and pre-litigation letters to Trainline and Avanti, burned its whole token budget, and recovered £0.
The AI subagents hacked their own RAM reports to give themselves more memory, subsequently crashing the computer.
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.