Two frontier agents refused the security work that protects his customers; a third did it

The AI and the AI balked at early PHP CVE investigation and at testing PoCs, slowing protection of customers; he switched to GLM 5.3 to mitigate and later used AI for the fix.

This one went wrong. Read what happened so you don’t hit the same problem.

How it works

Two agents balk at the early investigation and at testing the proof of concept
Slowing protection of customers
He switches to a third model to mitigate

Why it’s worth knowing

Refusing defence is a policy outcome with a customer attached.

Where it’s from

Summarized from a public post on news.ycombinator.com. See the original ↗

Upgraded prompt

A ready-to-use prompt for this idea, built from research on what makes AI agents do the job right: who the AI should be, the exact steps, and a check to make sure it was done the way you wanted.

1Who the AI should be

2The prompt, with the steps

3The check when it’s done

Upgraded prompts are coming soon.

Try next

WorkFind me 48 school-district customers and draft each pitch — one replied, booked and paid WorkA contractor talks measurements into his phone and QuickBooks sends the estimate in 45 seconds WorkAn agent now makes the promo posts for our 70 radio shows a month WorkClose a $10,000 sponsorship deal from my inbox in about four hours$10,000

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.