Comment by preommr
3 days ago
> It made sense to me that the persuasion principles I learned in Robert Cialdini's Influence would work when applied to LLMs. And I was pleased that they did.
No, no. Stop.
What is this? What're we doing here?
This goes past developping with AI into something completely different.
Just because AI coding is a radical shift doesn't mean everything has changed. There needs to be some semblance of structure and design. Instead what we're getting is straight up vodoo nonsense.
> what we're getting is straight up voodoo nonsense
Maybe not in this case.
For the AI to create a solution, it has to come up with a vector for your intention and goals. It makes some sense for an AI trained on human persuasion materials (basically, everything has a rhetorical aspect) to also track human persuasion features for intentions.
However, results will vary. Just as people trying to deploy rhetorical techniques (and ridiculous power stances) often come off as foolish, I believe trying to hack your intention vector with all-caps and super-superlatives won't always work as intended (pun intended).
Still, if you find yourself not getting what you want, and you check your prompt and find some persuasion feature missing (e.g., authority), I think it's worth trying to add something on point.
> It makes some sense for an AI trained on human persuasion
Why?
> However, results will vary.
Like in voodoo?
I'm sorry to be dismissive, but your comment is entirely dismissing the point it's replying to, without any explanation as to why it's wrong. "You are holding it wrong" is not a cogent (or respectful) response to "we need to understand how our tools work to do engineering".
> Instead what we're getting is straight up vodoo nonsense.
It always has been. Starting with the term "AI" itself.
Articles like these read the same way to me as any OpenAI announcement from the past 5 years. A bunch of technical mumbo jumbo laced with hyperbole, grand promises of how the technology is changing the world, and similar platitudes. I've learned to filter most of it out.
Occasionally I'll stumble upon an actually useful and practical tidbit of information which I can apply in my own workflow, which does involve LLMs, but most of the time it's just noise.