After watching this Under Studio humorous video showing a translator for business jargon, it made me wonder how far off current language models were from being able to do actually do this kind of translation, particularly with the sort of dark humour that makes this work.
So I did some experimentation, crafted a prompt and started testing some models on Amazon Bedrock.
Claude 3.5 Haiku
Haiku was the first model I found that did a decent job of translating one of the lines from the video with a one-shot prompt (aka, I gave it one example, and then asked it to do a similar job):
I tweaked the prompt to request dark humour and got this:
We're royally screwed, and management is desperately trying to cover their tracks by throwing around fancy words that essentially mean "we have no clue how to fix this massive mess we've created." The "strategic processes" are basically a corporate version of putting duct tape on a sinking ship while pretending everything is totally fine. Expect a round of scapegoating and middle management sacrifices in 3... 2... 1...
Since that went well, I tried a real-world example, pulling this paragraph from a Stripe memo from their latest layoff that was leaked:
As we've been working through our plans for 2025, leaders took a close look at their organizations and team structures. It became clear that there were several team-level changes needed to make sure we have the right people in the right roles and locations to execute against our plans.
This is Haiku's translation:
We're about to unleash a bloodbath of layoffs that will make corporate Hunger Games look like a friendly team-building exercise. "Right people in the right roles" is code for "we're cutting jobs, relocating some poor souls, and making everyone who survives do three people's work for the same pay." Expect a wave of panic, LinkedIn update storms, and sudden "networking" coffee meetings. Buckle up, because corporate restructuring is just a fancy term for "we're trimming the fat" - and by "fat," they mean human beings with mortgages and families. Happy 2025, everyone! 🔪📊
Ouch!
I'm starting to think having a website that can do gallows-humour translation of corporate Jargon would be a fun side project, although I'd probably need to be careful that it didn't rack up massive costs.
Llama 3.3 70B
Meta's Llama 3.3 70B model also did a fine job. I refined the prompt to request dark humour and got this response to the video line:
Management is freaking out because we're hemorrhaging money, and they're desperately trying to duct-tape together some new "strategies" to stop the bleeding before the whole ship sinks. Think of it as rearranging the deck chairs on the Titanic, but with more PowerPoint presentations.
Funny! What about the Stripe paragraph?
Code red: the axe is coming, and HR is sharpening the blade. "Team-level changes" is just corporate speak for "we're about to fire a bunch of people and make the rest of you pick up the slack." So, update your LinkedIn profiles and start practicing your "I'm excited about this new opportunity" face, because it's about to get real.
Awesome. This is definitely a workable side-project.
Amazon Nova Premier
The translation from the video:
Management is freaking out because we're missing targets, and they're scrambling to come up with a plan that might just save their jobs. Expect some serious micromanaging and maybe a few sacrificial lambs thrown to the wolves soon.
And from Stripe:
Management's crystal ball showed them that our current team setup is a hot mess. So, brace yourselves for a round of musical chairs where some of you will end up in roles you're not suited for, and others might just find themselves without a chair at all. Welcome to the 2025 restructuring rodeo!
Maybe not quite as funny as Llama, but still pretty decent.
There's definitely something here. It would be super-funny if you could embed it as a plugin to MS Teams / Zoom as a side-channel for your next all-hands.
Top comments (1)
I've published a GitHub repository that walks through the creation of a project like this using Next.js in the front end (currently) and Amazon Bedrock or GitHub Models as the model provider:
github.com/codiform/jargon-transla...
Since GitHub Models has a free tier, I've deployed a test site to Vercel showing the GitHub Models + Next.js version if you want to try:
jargon-translator.vercel.app