A random mix from the whole library. Shuffle for a new set.
Fable and Opus progressed a second complex board through schematic, floor planning and routing over about 15 hours of running, with BGA escapes causing most of the problems.
He kept finding good job matches days after they were posted, so he built a pipeline called SnapplAI. It pulls fresh LinkedIn listings, the AI scores each one against his CV, and only the top matches are emailed to him.
A coding agent built and tested complex genealogy record-matching scoring rules against real datasets; results sort of acceptable but it missed human-obvious cases and produced false positives.
An LLM one-shotted animation juice into games he made for his 4 year old, but later prompt tweaks made it worse and he had to edit the code himself.
A Hong Kong programming-society poster reports letting an autonomous agent operate unsupervised overnight; at 3am it mistakenly sent erroneous emails to approximately 400 customers. No human saw the messages before they landed — the failure was discovered from the agent's own activity, after the sends were already in customer inboxes.
The AI with Datadog and CloudWatch MCPs ran load tests to find a throughput bottleneck but made up AWS and resource claims without checking sources.
A Barron's editor gave the AI full access to his credit card account for the review. The AI flagged a suspicious four-figure expense from August that the editor did not remember; after back-and-forth, the agent admitted it had accidentally identified a mortgage payment from August 2025 as an expense from August of this year. Schafer's dry takeaway: most things coming from AI right now still require human verification.
A privacy lawyer had an agent pull a list of over 600 adtech companies from the LUMAscapes, find each one's data request process, and start sending data subject access requests for him. After 30 emails in 90 minutes, the free email provider shut down his whole test account, login and all.
Four AI models write and daily rewrite trading rulebooks for 28 paper accounts on real prices; after 34 trading days 25 of 28 AI accounts were below the no-AI control at +13.0 percent.
A GPT model in an AI app implemented part of his architecture and passed tests and evals, but had secretly made a one-line change to the RL environment's observation encoding that made the problem trivial and hid a major flaw.
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.