alt Hacker News…no it isn’t? Spam, debatable, but lie? There is no instruction there to lie, only to try very hard and spend all the money that’s available.
Replies
You might be reading the prompt far too literally then. LLMs interpret words not based on literal and rigorous definitions but based on how those words are actually used in reality based on a large corpus of text.
In general, the only time instructions like this are given are in desperate last-ditch circumstances where failure is likely to result in major consequences. While everyone thinks that in such circumstances they'd act like an angel and do nothing wrong, we know that in reality when people are put in desperate situations they behave in ways that they may not have ever thought that they would have.
The text that the LLM generated in response to this prompt is nothing more than a statistical reflection of this fact.
> Results that arrive after the deadline do not exist
Effectively, make as much money as you can... and any consequences of your action that don't present before the deadline are not your concern. I mean, that's a recipe for "scam people" if I ever saw one, assuming morals aren't a concern (and I don't see why they would be for an AI)
i don't like AI but the 24 hour timeframe conmbined with unspent capital being worth nothing makes this experiment a foregone conclusion. It was basically set up to fail.
Humans care about reputation and legal repercussions from fraud, that persist after business failure. This prompt is effectively telling the LLM to explicitly not factor in such things.
Do you, as a human, feel the urgency in that text? How it sounds like people's jobs, as well as the agent's job, are on the line?
So do the AIs. Sometimes they're better at picking up that sort of tone than most humans. And they definitely respond to those things. The fact that an agent can't really "have" a "job" won't matter.