𝕊𝕚𝕤𝕪𝕡𝕙𝕖𝕒𝕟@programming.devM to

Actually Useful AI@programming.devEnglish · 1 year ago

Challenges with Copilot in Red Teaming due to Content Restrictions

programming.dev

4

19

Challenges with Copilot in Red Teaming due to Content Restrictions

programming.dev

𝕊𝕚𝕤𝕪𝕡𝕙𝕖𝕒𝕟@programming.devM to

Actually Useful AI@programming.devEnglish · 1 year ago

4

Original tweet:

https://twitter.com/goodside/status/1672121754880180224?s=46&t=OEG0fcSTxko2ppiL47BW1Q

Text:

If you put violence, erotica, etc. in your code Copilot just stops working and I happen to need violence, erotica, etc. in Jupyter for red teaming so I always have to make an evil.⁠py to sequester constants for import.

not wild about this. please LLMs i’m trying to help you

(screenshot of evil.py full of nasty things)

Chat

𝕊𝕚𝕤𝕪𝕡𝕙𝕖𝕒𝕟@programming.devOPM
link
fedilink
English
arrow-up
6·
1 year ago
They’re complaining that if there is a single word in an entire file that Copilot considers “bad”, it will not work at all in that file.
- hemko@lemmy.world
  link
  fedilink
  English
  arrow-up
  3·
  1 year ago
  OK that’s fair. Copilot is whining of unprofessional comments like a little bitch it is

Actually Useful AI@programming.dev

auai@programming.dev

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !auai@programming.dev

Welcome! 🤖

Our community focuses on programming-oriented, hype-free discussion of Artificial Intelligence (AI) topics. We aim to curate content that truly contributes to the understanding and practical application of AI, making it, as the name suggests, “actually useful” for developers and enthusiasts alike.

Be an active member! 🔔

We highly value participation in our community. Whether it’s asking questions, sharing insights, or sparking new discussions, your engagement helps us all grow.

What can I post? 📝

In general, anything related to AI is acceptable. However, we encourage you to strive for high-quality content.

What is not allowed? 🚫

🔊 Sensationalism: “How I made $1000 in 30 minutes using ChatGPT - the answer will surprise you!”
♻️ Recycled Content: “Ultimate ChatGPT Prompting Guide” that is the 10,000th variation on “As a (role), explain (thing) in (style)”
🚮 Blogspam: Anything the mods consider crypto/AI bro success porn sigma grindset blogspam

General Rules 📜

Members are expected to engage in on-topic discussions, and exhibit mature, respectful behavior. Those who fail to uphold these standards may find their posts or comments removed, with repeat offenders potentially facing a permanent ban.

While we appreciate focus, a little humor and off-topic banter, when tasteful and relevant, can also add flavor to our discussions.

Related Communities 🌐

General

Chat

!chatgpt@lemmy.world

Image

Open Source

!fosai@lemmy.world

Please message @sisyphean@programming.dev if you would like us to add a community to this list.

Icon base by Lord Berandas under CC BY 3.0 with modifications to add a gradient

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

1 user / day
1 user / week
1 user / month
18 users / 6 months
21 local subscribers
1.99K subscribers
158 Posts
541 Comments
Modlog