A Facebook group author reports using AI to renegotiate internet pricing across four accounts: The AI researched competitor offers and contacted providers via web chat, cutting AT&T home internet from $94.99 to $40/mo (after two free months), lake-house Spectrum from $130 to $60 with a year of free cell service, office Spectrum from $110 to $60, and MHP internet from $110 to $70 with a free phone replacing a separate $60 cell bill — $275/mo combined, ~$3,400 first-year savings.
During the Apple event she had the AI check the live transcript every five minutes against her client roster. It flagged a Siri announcement as a fit for her voice AI client, and she got pitches out right away.
Told Kimi to set up a local Matrix server and write a Claw-like agent system with read-only email tools, Matrix messaging, heartbeat memory consolidation and reminders, now running his agents.
His podcast ran for 21 years and more than 1,000 episodes in 4 languages. The new site at pomcast.com keeps 154 videos in under 4 MB of plain HTML, and it lists the 121 episodes that only survive in his backup and the 111 that seem lost.
A Persian-language reel demonstrated the AI managing emails and sending auto-replies, handling Instagram direct messages and comments, generating full page analytics with growth charts, and producing weekly content plans — then creating a custom avatar and a product video for a QCY SP2 Bluetooth speaker. It connected to Gmail and Instagram.
He had wanted an automatic provisioner for his boards for a long time but it was a whole project on its own, so he told the AI to write it. Some physical steps still need him, but each board now takes 2 to 3 minutes instead of a few stressful hours.
A shipwithmuse automation recipe has the AI find dead follows: the agent checks the last activity date of every profile you follow on Instagram and returns a list of inactive ones to unfollow.
The AI built the gear calculations and STL, DXF and SVG exporters for his Free Pascal Gear Designer program for machining and 3D printing, which worked basically flawlessly.
In someone's 'What Went Wrong #1' log, an AI wrote 'SAVE 30%' onto two bundle listings on day 3 — but the bundle math was wrong, the saving didn't exist, and other checker agents missed it, so a false price claim stayed live on the shop for days. The fix was a new 'Listing Watch' agent that re-checks every price claim against the real numbers each morning.
This one went wrong. See what happened before you try it.
The same man's system pulls every train, flight, hotel and ferry booking out of his email into one travel database. The AI answers his trip questions from it, sends his e-tickets to WhatsApp on the morning of travel, and messages him when there are delays. He averages about 300 pounds a month in delay claims and plans to have it file those next.
He had already written the handout for an upcoming presentation. He opens PowerPoint and has the AI build the slide deck from that material, using his own template.
The reviewer has the AI check his flight seats every 30 minutes; he can let it change the seat automatically or have it prompt him with the choice first.
Chris Pirillo published a scorecard of 57 build jobs run on the AI 4 (via Antigravity, about $200/month): 11 succeeded, 31 changed nothing, 148 rounds were wasted, and 52 jobs needed the AI to finish them.
This only partly worked. Worth knowing before you try it.
Neo Tsang recounts uploading room photos and an inventory to the AI a month before moving; the AI categorised everything by usage frequency into keep, donate and discard, with a room-by-room packing sequence. He also had the AI break down three movers' quotes line by line and picked the middle option at nearly half the most expensive quote (the post closes with a referral code).