Agents shrank his AI model container from 6 GB to 900 MB and off the GPU
LLMs migrated a 6GB GPU SciBERT container to a 900MB ONNX CPU container.
A random mix from the whole library. Shuffle for a new set.
LLMs migrated a 6GB GPU SciBERT container to a 900MB ONNX CPU container.
His business scans every invoice into a Google Drive folder. The AI reconciles them there: checking they were billed correctly, that credits for returned goods actually arrived, and that there is no slippage. He says it is far faster than reconciling by hand.
He had the AI watch his online trainings and take the tests for him, and he collected 40 certificates in one day. He told it not to get perfect scores every time, and he says the system is broken if this works.
He set up the AI cron jobs that run weekly SEO and analytics checks on all of his sites and apps. He says the checks are working well and keep him consistent.
Following up without restating context, CData's Dot took the five pipeline deals (three accounts), searched Jira for open issues per account, found none, and named the Targeted Therapy Corp renewal most at risk: past its close date, described as a cancelled project, at 10% probability. The post says the same answer by hand can take days of asking engineering and searching two systems.
Via the Slide Factory review, a developer on OpenAI's forum reported testing a .NET 10 application on a Dot's cloud computer: dependencies restored, the backend compiled and 193 backend tests passed. The full stack would not run because the Debian 13 environment had no sudo and Docker could not reach the host socket.
Had the AI build an open-source source control system, benchmarked on a 100k-file monorepo as 12x faster sparse checkout and 82x higher concurrent land throughput than git.
In 'Using the AI for Business' Ep. 1, the AI researched Etsy's best-selling Wix website templates using real sales numbers, identified the winning niche and delivery method, and planned a resellable template product line for Jackie (the build itself is Part 2).
He made a tool for students that started as a simple quiz solver extension and grew slowly to just over $100 in monthly recurring revenue, with very little marketing. A month ago he reverse engineered Anki using AI, so anyone can bring their Anki deck and study it in his tool. He says that is the thing that worked.
With the AI doing the grunt work he built a compiler for his own language that runs on Mac, Linux and Windows and cross-produces for those plus WASM, iOS, Android, Zynq, m68k and 6502, with a signed binary running on his phone.
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.