Pictured above: a screenshot from a conversation I had with Claude last night. I was using it to craft an email in response to an interview that could be better described as an ambush.
I use LLMs as a double-check for when I’m trying to remain professional when greatly annoyed and for when I want to spend the minimum amount of time on something or someone. The party I was communicating with met both criteria.
I’m pretty sure that the way I sass back at LLMs doesn’t affect the quality of their revision when I harshly tell them that I disagree with their original answer. But as a catharsis, creative outlet, and excuse for an amusing screenshot and blog post, it’s oh-so-good.
The screenshot above is another regular reminder from Yours Truly that the LLM isn’t always right, but the final decision is always yours. Sometimes, you need to sass back — not necessarily to get better results, but to remind yourself not to abdicate completely to AI.
In case the first line in my prompt sounds familiar, but you can’t place it, here’s the source:
There are four such ads, each one featuring two actors, with one playing the part of the user, and the other playing the part of ChatGPT. The acting is perfect, with the user clearly in need of answers, and ChatGPT with slightly delayed responses delivered in a saccharine tone and a creepy smile at the end (“Give me your creepiest fake smile!” must’ve been part of the audition process). All the ads end with a snippet of the rap version of Blu Cantrell’s 2003 number, Breathe, which features Sean Paul and one of the best beats from that era.
I’ve posted the four ads below, from my least to most favorite. Each one features a common LLM use case.
Here’s Treachery, where a student is asking ChatGPT to evaluate her essay:
Deception features ChatGPT providing advice on the user’s business idea:
Violation’s user wants a six-pack — the muscle kind, not the beard kind — and is about to regret telling ChatGPT his height:
And my favorite, Betrayal, starts with the user trying to get closer to his mom, and ends on a cougar-riffic note:
OpenAI CEO and owner of the world’smostpunchablevoice Sam Altman is, as the kids say, crashing out over these ads, calling them “dishonest” (they’re more hyperbolic) and “authoritarian” (which is Altman himself being hyperbolic):
Here’s your start-of-the-year reminder that you don’t have to accept your LLM’s answers as gospel. In fact, you do what I do — talk back to them Samuel L. Jackson / Nick Fury from The Avengers-style.
The screenshot above comes from an exchange I had with Gemini earlier today. I like using LLMs as a sounding board for ideas — as I like to say “the one thing you can’t do, no matter how creative or clever you are, is come up with ideas you’d never think of.”
Gemini suggested a course of action that I completely disagreed with, so I decided to respond with one of my favorite lines from the first Avengers film, and it responded with “touché.” Keep thinking, and don’t completely outsource your brain to AI!
And just as a treat, here’s that scene from The Avengers:
Want more? Here’s a post from January about what I call The “Nick Fury” method for refusing LLM answers.
