Re: [Last-Call] Re: [EXTERNAL] Re: L2 posting rights restriction

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Me: why not use AI to monitor a problematic poster on a mailing list?

ChatGPT:

Using AI to monitor problematic behavior on a mailing list is definitely a possibility and has been explored in various contexts. AI can help in several ways:

1. **Content Moderation**: AI algorithms can scan messages for inappropriate content, such as hate speech, harassment, or spam, and flag them for review by moderators.

2. **Behavior Analysis**: AI can analyze patterns of behavior, such as frequency of posts, language used, or interactions with other members, to identify potential problems or conflicts.

3. **Early Detection**: AI can detect emerging issues or conflicts before they escalate, allowing moderators to intervene early and prevent further disruption.

4. **User Profiling**: AI can create profiles of individual users based on their posting history and behavior, which can help moderators identify repeat offenders or problematic users.

However, it's important to note that AI is not perfect and may not always accurately identify problematic behavior. Additionally, there are ethical considerations to take into account, such as privacy concerns and the potential for algorithmic bias. Therefore, while AI can be a useful tool for monitoring mailing lists, it should be used in conjunction with human moderators who can provide context, judgment, and oversight.

On Mon, Jun 10, 2024 at 9:53 PM Brian E Carpenter <brian.e.carpenter@xxxxxxxxx> wrote:

On 11-Jun-24 15:50, Rob Sayre wrote:
> On Mon, Jun 10, 2024 at 12:59 PM Gorsic (US), Bonnie L <bonnie.l.gorsic@xxxxxxxxxx <mailto:bonnie.l.gorsic@xxxxxxxxxx>> wrote:
>
>     Why not use AI to monitor his posts and if offensive words are used, don’t allow them on the list?
>
>
> Interesting. I suggest you write up an Internet-Draft describing this idea in more detail.

Let's try the running code approach. Here's my recent dialogue with ChatGPT. I was slightly amazed:

Brian:

Please decide if the following message text meets normal professional standards: "<text of the message in question>"

ChatGPT:

The message text does not meet normal professional standards. The comment on <name>'s appearance is inappropriate and unprofessional in a work-related context. The invitation to lunch could be seen as personal rather than professional, particularly when paired with the preceding comment. Here is a revised version that maintains professionalism:

"Thanks, <name>. I appreciate your help with this matter. Perhaps we could catch up over lunch at the next IETF meeting to discuss our projects further?"

    Brian


[Index of Archives]     [IETF Annoucements]     [IETF]     [IP Storage]     [Yosemite News]     [Linux SCTP]     [Linux Newbies]     [Mhonarc]     [Fedora Users]

  Powered by Linux