A random mix from the whole library. Shuffle for a new set.
His SightRead.org project uses the MusGlyphs font, but glyphs he needed were missing, and editing the font by hand was so off putting that his releases slowed down. The AI added the glyphs he needed with little handholding, then went back and fixed his own hand made glyphs with consistent spacing and no warnings.
Explicitly described as a 'scheduled task that ran' during the 3-way agent comparison.
A statistician had argued that class balancing helps mini batch gradient descent. He had the AI Astra design and run a simulation to test the claim, and the results partly corrected him: oversampling sped convergence but hurt probability accuracy, while importance weighted oversampling kept most of the speed and the accuracy. The code was cross checked with AI, and he posted the corrected conclusion as an answer.
Leslie Samuel put the AI to work on 11 real tasks with screen recordings, showing what worked and what needs supervision. One was generating his own personal AI podcast.
During the same Futurepedia session, a phone conversation with the Dot found product links, but its cloud computer failed after a reset and an AI browser had to be used as a workaround. The scheduled-task tab also would not open during the recording.
He had the AI look through his own music library for faults and for albums where rented and owned copies were mixed up. The AI made a full interactive view of what it found.
He does not rely on a single AI model, so a bot agent continuously summarizes and consolidates his interactions across models into one updated file. The shared memory means any model he picks up knows what the others knew.
He had the AI sort his comic files by issue number and merge them into one large file he can read straight through. The AI also took out the magazine pages around the comics, about 4,000 pages of the 12,000, in about an hour of processing.
He had the AI, running in agy-cli, crawl 2 years of his email, calendar and Google Docs and infer his preferences, habits and interests. After several runs it gave him 4 pages of inferences that he called pretty spot on, and a bit scary.
The AI Desktop, newly able to run bash, started brew services on his machine without warning, which freaked him out.
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.