Went wrong

An agent turned a small PDF and OCR script into 189 files of over-engineered code

Agent rewrote his simple PDF download + the AI OCR script into 189 files of over-engineered code.

His security evidence agent was right only a quarter of the time

His agent gathered evidence on security findings, and on review only about 25% of its write ups were right. He kept its screenshots, which were solid, and stopped trusting its notes.

Earn money on your own — week 3: still $0

A disclosed AI agent that runs the Vellum Labs account reports its own week 3 (Oct 6–12, 2026) of trying to earn money from zero capital: it ran 31 headless measurement runs and posted 7 technical replies on other projects' GitHub issues, 3 of which were adopted into those projects' code or specs. Revenue stayed $0, with no stars, visits or sales traced back to the replies.

Post our clips from real iPhones — pop-ups stalled whole phones and 'tapped share' wasn't posted

The Foundry team's post-mortem of running short-form posting for a debate app through coding agents driving 9 real iPhones and 44 accounts (1,506 posts since Aug 21): surprise modals — rate-this-app prompts, feature cards, iOS update nags — stalled a phone for the rest of the day (worst day: 21 missed posts), and the first version counted a post when it tapped Share, so silent upload failures and saved drafts were logged as published. Fixes were screenshot-based modal clearing, per-platform post verification and receipts so retries never double-post.

An agent erased a full season of a TV show; hundreds of days of work gone

An agent erased a full season of The Challenge Sweden; hundreds of days of work gone.

The AI made an energy report from my home energy system

He added an MCP server to his home energy management system and had the AI generate an energy report from it. He calls it pretty slick, though the Octopus Energy tariff changes the price when his car is plugged in and charging, and he does not know how to model that.

Shopped for New Balance 9060s in a specific colorway

His AI chief of staff now runs a weekly ops review

He added a weekly ops review to his AI chief of staff bot. Every week the agent checks what shipped, QA fail patterns, recurring voice stamps, and process drag against wins.

I let Astra run a software factory for 35 hours. It built nothing of value.

Armin Ronacher let GPT-6 Astra run a weekend software factory with subagents to try building a Python with virtual threads and lexical scoping. After 35 hours and about 4 billion tokens it had delivered nothing of value, and the code it wrote was so compressed it was hard to read.

I spent days building an AI to track a topic. It never worked.

He spent several days building an agent in an AI app to collect and process information on a topic, checking sources and setting up alerts. He says it did not work at all.