An overnight fuzzing run found 26 kernel crashes, with fixes, some already upstream
Kimi told overnight to fuzz Linux kernel filesystem code produced 26 crashes with reproducers and fixes; some have already landed upstream.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,691 ideasAgents read 206 of my AI sessions and found 223 failures
Haiku 5.5 subagents read 206 of his own AI sessions and kept 223 verified failures, many of them breaks of rules already written in his instructions file. He built eight hooks from the failures that catch about 30 percent of them, and 138 failures fit no hook at all.
This only partly worked. Worth knowing before you try it.
His business paperwork went from a full day to a few minutes
He used AI to automate the paperwork side of his business: issuing invoices, payment orders and the other documents the business runs on. The work used to take a whole day. Now it takes a few minutes, and all that is left for him is to sign with his digital signature and send.
The AI built a failover for his busiest app in 2 minutes and saves him about 200 dollars a month
The AI built a primary/secondary API callout in 2 minutes after he ported his busiest app stage to Haiku, saving about 200 dollars a month.
$200a month
The AI made narrated English and French versions of his project video in about an hour
AI session of about 60 minutes produced narrated English and French video versions for his project for about 30 dollars at API rates, with reusable assets.
$30
Store wired an AI agent into live order data; daily support fell from 3+ hours to under 30 minutes
Order-tracking and returns questions made up roughly 60 to 70 percent of this store's support tickets, so they connected an AI agent directly to their Shopify order data so it pulls real tracking information and answers customers automatically. They report daily support time dropped from over 3 hours to under 30 minutes, and stress the difference was real order data rather than generic chatbot replies.
The agent-built data pipeline he inherited was full of errors and its fixes made new ones
The agent-built data pipeline he inherited was riddled with errors and producing bad data, and the coding agent's fixes typically introduced new defects.
This one went wrong. See what happened before you try it.
An agent spent two weeks removing duplicate caches and tidying an old codebase
Agent refactored old code over two weeks, removing and consolidating duplicate client-side caches and tidying the codebase (Composer 2.5 via Cursor).
My podcast episode was edited mostly by my AI agent
He has edited his podcast Rebuild by hand for years, and nearly everything after importing the recordings was manual. For the latest episode, the AI reverse engineered Logic Pro's ProjectData file so the editing could be automated, and the agent did most of the edit.
He and the AI measured his agent sessions and found long sessions cost double per turn
He and the AI analysed 144 of his CoWork sessions and 14,640 turns, found a turn past turn 141 costs 2.1x an early turn, and stopped batching sessions as a result.
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.