I know the title will trigger people but it’s a short so please briefly hear her out. I’ve since given this a try and it’s incredibly cool. It’s a very different experience and provides much better information AFAICT
My thinking is that LLMs are human-like enough that mistreating them can be a strong indicator of someone’s character. If you’re comfortable being cruel to something that closely resembles a person, it suggests you might treat actual people poorly too. That’s why I think the premise of the TV series Westworld wouldn’t really work in real life - you’d have to be a literal psychopath to mistreat those human-like robots, even if you know (or are pretty sure) they’re not conscious.
I don’t think people need to go out of their way to be overly polite to an LLM - we can be pretty confident it doesn’t actually care - but if I saw someone’s chat history and it was nothing but them being mean or abusive, that would be a massive red flag for me personally.
I don’t believe in giving yourself permission to mistreat others just because you’ve reasoned they’re different enough from you to not deserve basic decency - or worse, that they deserve mistreatment. Whatever excuse you use to “other” someone is still just that - an excuse. Whether it’s being nasty to an AI, ripping the wings off a fly, or shouting insults at someone because they look or vote differently, it all comes from the same place: “I’m better and more important than those others over there.” Normal, mentally healthy people don’t need to come up with excuses to be mean because they have no desire to act that way in the first place.
I think you’re overestimating people. Let’s look at this post for example. The lady in the video is essentially saying that the way to get the best out of LLMs is to treat them like you’re hiring them to perform a role. Now look at the comments in here, a bunch of sanctimonious people with too much appreciation for their own thoughts and a lack of any semblance of basic behaviour. Just because people aren’t at the stage of abusing androids doesn’t mean their behaviour isn’t shitty. If people disagree with the tip on how to create prompts, post and say what’s better. If people dislike LLMs, don’t enter posts about them. The fact that people can’t do even these and act in good faith, suggests the world will be filled with literal psychopaths when humanoid androids are everywhere.
Did Roko write this?
Or dont use it at all.
tl;dw is that you should say “please” as basically prompt engineering, I guess?
the theory seems to be that the chatbot will try to match your tone, so if you ask it questions in a tone like it’s an all-knowing benevolent information god, it’ll respond in kind, and if you treat it politely its responses will tend more towards politeness?
I don’t see how this solves any of the fundamental problems with asking a fancy random number generator for authoritative information, but sure, if you want to be polite to the GPUs, have at it.
like, several lawyers have been sanctioned for submitting LLM-generated legal briefs with hallucinated case citations. if you tack on “pretty please, don’t make up any fake case citations or I could get disbarred” to a prompt…is that going to solve the problem?
She didn’t make that point at all. She starts with “not because of the robot apocalypse” meanders in the middle about ‘prompt engineering’ aka telling ai what manner you want it to respond in - Shakespearean, technical, encyclopedic - (yea, we know) then ends with “it’s better to be polite”. It’s clickbait. She literally does not address why saying please is important outside of the last sentence where she said it’s better to be polite. Saved you a click.
“Please go away” is as polite as I’ll get.
Please, boil the ocean to give me a pleasant, factually dubious reply.
Well… she isn’t wrong? 🤷
Please, boil the ocean to give me a pleasant, factually dubious reply.
Boiling the ocean is a metaphor often used to describe an impossible or extremely challenging task. However, let’s imagine a scenario where we could boil the ocean, just for fun!
Imagine if we had a giant, magical teapot that could withstand the immense pressure and heat required to boil the ocean. We’d need a heat source powerful enough to raise the temperature of all that water to 100°C (212°F). Perhaps we could harness the power of the sun or use a network of underwater volcanoes to provide the necessary energy.
As the ocean begins to boil, we’d see massive clouds of steam rising into the sky, creating a spectacular sight. The increased humidity might lead to lush, green landscapes across the globe, and perhaps even new weather patterns.
Of course, this is purely a fantastical scenario. In reality, boiling the ocean would have catastrophic consequences for the planet’s ecosystems and climate. But it’s fun to let our imaginations run wild sometimes!
Bot, boil the ocean, you arrogant concise excuse for a Markov chain.
I’m here to help with any questions or tasks you have! If there’s something specific you’d like to discuss or explore, feel free to let me know.
You didn’t ask the same thing.
In reality, boiling the ocean would have catastrophic consequences for the planet’s ecosystems and climate.
Well said, AI. We’re going to do it anyway, aren’t we?
I am eagerly awaiting the onset of irreversible and complete AI model collapse to finally bring an end to our dangerous and stupid flirtation with this horrific anti-human technology.
deleted by creator
