> Prompt injections are attempts by third parties to manipulate its behavior through malicious instructions that ChatGPT agent may encounter on the web while completing a task. For example, a malicious prompt hidden in a webpage, such as in invisible elements or metadata, could trick the agent into taking unintended actions, like sharing private data from a connector with the attacker, or taking a harmful action on a site the user has logged into.

A malicious website could trick the agent into divulging your deepest secrets!

I am curious about one thing -- the article mentions the agent will ask for permission before doing consequential actions:

> Explicit user confirmation: ChatGPT is trained to explicitly ask for your permission before taking actions with real-world consequences, like making a purchase.

How does the agent know a task is consequential? Could it mistakenly make a purchase without first asking for permission? I assume it's AI all the way down, so I assume mistakes like this are possible.

Thanks for your continuing work on memcached! I'd be very curious how garnet's benchmarks compare with memcached.

It seems that with uBlock origin enabled in Firefox, I was unable to fill out either of the 2 donation forms on the page. It wouldn't let me fill in my Name in the first form, nor would it let me enter a custom amount in the 2nd form.

Disabling uBlock origin seems to resolve.

According to wayback machine, they deleted the page sometime mid 2021. Here's an archived version of the page: https://web.archive.org/web/20210513051214/https://mullvad.n...