News for hackers. Stuff that matters.

A comment on Microsoft 365 Copilot – your copilot for work. Parent comment

Re:Microsoft 365 Copilot – your copilot for work by galaxytachyon on Thursday March 16, 2023 @12:38PM (#35184415)
There are built in guardrails. Those are so strong it effectively lobotomized the LLM and force to abort its own internal process in favor of just saying: "I am sorry Hal, I afraid I can't do that".

Try to make ChatGPT or Bing to even attempt to write a snarky and negative email to your coworkers. It will refuse to do so.

Jailbreak attempts may work, but with how strong the guardrails are, it is unlikely you can consistently succeed. And any failed attemps can be report to sysadmins and forwarded to HR. Too much risk.

[ Parent | on HN ]
Re:Microsoft 365 Copilot – your copilot for work by theGnuMe on Thursday March 16, 2023 @01:34PM (#35185263)
The British figured out long ago how to insult someone with praise. This is why British comedy is so good. They have use such creative discourse to call out their politicians without libeling them as the liars they are.
[ Parent | on HN ]