The responses aren’t exactly deterministic, there are certain attacks that work 70% of the time and you just keep trying.
I got past all the levels released at the time including 8 when I was doing it a while back.
The responses aren’t exactly deterministic, there are certain attacks that work 70% of the time and you just keep trying.
I got past all the levels released at the time including 8 when I was doing it a while back.
deleted by creator
Now I’m upset this wasn’t the original haha
I’ve definitely experienced this.
I used ChatGPT to write cover letters based on my resume before, and other tasks.
I used to give it data and tell chatGPT to “do X with this data”. It worked great.
In a separate chat, I told it to “do Y with this data”, and it also knocked it out of the park.
Weeks later, excited about the tech, I repeat the process. I tell it to “do x with this data”. It does fine.
In a completely separate chat, I tell it to “do Y with this data”… and instead it gives me X. I tell it to “do Z with this data”, and it once again would really rather just do X with it.
For a while now, I have had to feed it more context and tailored prompts than I previously had to.
Collective mass arbitration is my favorite counter to this tactic, and is dramatically more costly for the company than a class action lawsuit.
https://www.nytimes.com/2020/04/06/business/arbitration-overload.html
A lot of companies got spooked a few years back and walked back their arbitration agreements. I wonder what changed for companies to decide it’s worth it again. Maybe the lack of discovery in the arbitration process even with higher costs?