Regardless of OpenAI’s current success — significantly with the widespread use of ChatGPT — the corporate’s applications aren’t good, and like several new know-how, there are going to be bugs that should be mounted.

This week, the factitious intelligence firm introduced it is going to be rolling out a “Bug Bounty Program” in partnership with Bugcrowd Inc., a cybersecurity platform. This system calls on safety researchers, moral hackers, and “know-how fanatics” to help in figuring out and reporting issues (in change for money) to assist OpenAI handle vulnerabilities in its know-how.

“We make investments closely in analysis and engineering to make sure our AI programs are protected and safe,” the corporate said. “Nonetheless, as with every complicated know-how, we perceive that vulnerabilities and flaws can emerge. We consider that transparency and collaboration are essential to addressing this actuality.”

We’re launching the OpenAI Bug Bounty Program — earn money awards for locating & responsibly reporting safety vulnerabilities. https://t.co/p1I3ONzFJK

— OpenAI (@OpenAI) April 11, 2023

Compensation for figuring out system issues might be wherever from $200 to $6,500 based mostly on vulnerability, with the utmost reward being $20,000. Every reward quantity is predicated on “severity and affect” — starting from “low-severity findings” ($200) to “distinctive discoveries” (as much as $20,000).

Associated: What Enterprise Leaders Can Study From ChatGPT’s Revolutionary First Few Months

Earlier than outlining the scope of vulnerabilities that OpenAI needs to determine (and the ensuing rewards), the Bug Bounty participation web page states: “STOP. READ THIS. DO NOT SKIM OVER IT” to inform customers what sort of vulnerabilities can equal money.

Examples of vulnerabilities which can be “in-scope” and due to this fact eligible for reward are authentication points, outputs that consequence within the browser utility crashing, and information publicity. Issues of safety which can be “out of scope” and never eligible for a reward are jailbreaks and getting the system to “say unhealthy issues” to the person.

Screenshot of bugcrowd.com/openai.

Since launching this system, OpenAI has rewarded 23 vulnerabilities with a median payout of $1,054, as of Thursday morning.

The corporate additionally says that whereas this system permits for approved testing, it doesn’t exempt customers from OpenAI’s phrases of service, and content material violations may lead to being banned from this system.