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.
DR_Hero
joined 1 year ago
Excuse me but, the fuck is wrong with you?
The reason that makes the most sense in one of the articles I've read is that they fired him after he tried to push out one of the board members.
Replacing that board member with an ally would have cemented control over the board for a time. They might not have felt his was being honest in his motives for the ousting, so it was basically fire now, or lose the option to fire him in the future.
Edit: https://www.nytimes.com/2023/11/21/technology/openai-altman-board-fight.html
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.
At this point I'm pretty sure their strategy is to take the hit in search engine quality since they have a stranglehold there anyway, and spam everyone with AI so they can come out ahead on that front with Human feedback. It's pretty shitty, and the exact reason we would be taking down big tech monopolys.