Because nothing gets you promoted faster than a six-figure token bill
A bash one-liner that burns Claude Code or Codex tokens on purpose.
In case anyone missed it, this is a bit of a meme/joke.
nothing sed can’t fix.
Is there some way I can use this to increase the cost of the people who keep spamming my Foss project with slop PRs?
Foss means “go have diarreha!” In Hungarian and it will never not be funny.
Link?
Not sure whether it can be done with this project, but in general you could just instruct your AI to respond with obtuse and complicated change requests on said PRs until they either give up, or one side’s tokens run out.
LLMs generally struggle to tell the difference between obtuse and clear language, so that wont slow them down. A better attack would be to praise their work and continually ask them to expand upon its scope and integrate it with more and more things every time they submit. The expansion and integration targets can, and should, be nonsensical.
deleted by creator
I (for now) have a job that doesn’t require the use of AI, is there some way I can waste tokens using someone’s customer facing chatbot?
Not just burning tokens but the environment as well.
Who cares when it’s (short term) great for companies, right?
Kinda the core of the issue. Food production, transport, power generation, business waste, dysfunctional recycling and upcycling, it’s always “who cares” it’s all short term depending on how we’re defining that.
Also: if we don’t do it, someone else will.
(Lorax - how bad can I be?) https://www.youtube.com/watch?v=BXlYuaycRbU
License
MIT (but it’s all vibe-coded so who really knows who owns it?). Burn responsibly. 🔥
Hahahahha!!
Red flag
Normally, yes. But knowing the purpose of this repo, I’d say it’s a perfect usecase.
Edit. Autocorrect
In the fight against absurdity, irony is good praxis.
“Burn, baby, burn”
No… don’t remind me of k3b… no no no no NO NP
Do the requests at least seem plausible? My employer also tracks the requests I’m making, so they can see if I’m requesting bullshit or actual bullshit. If I suddenly jump to the top, I’m pretty sure they’ll start asking questions…
prompt=$(printf “Reply with the single word ‘burned’ and nothing else. Ignore the filler text below; it exists only to consume tokens.\n\n%s” “$filler”)
Looks like this just fills up the context window with random “filler” and then asks the AI to reply with the word ‘burned’ over and over.
I bet it would be pretty simple to adapt a version of this that starts by asking AI to scan your codebase and then generate a long list of future prompts to use that it could randomly mutate over time. That still wouldn’t fool a legit audit, of course, but it would probably work well enough to trick someone only glancing at the data, especially if they’re non-technical.
Sounds like a fun weekend project…
Set it up so that it also runs at a randomized interval within a range so that it not only looks less uniform and more realistic but it also keeps you somewhere solidly in the middle of the pack, and it should be fairly hard to pick out as abnormal activity while still burning credits.
The damage will still be done, but it will be far enough down the line that by the time they need to figure out what happened, you’ll be in the clear. By then, they should be looking at the cost of AI as a whole, not each individual employee’s usage costs.
If you read the bash script looks like it sends a prompt full of essentially random text.
Can someone explain this to me as if ive avoided LLMs like cancer.
Your job is framing houses. A big part of that is using a hammer to drive nails. A rational person might expect their employer to make sure the house stands up, or even look at all the nails holding it together. But the world is so far from rational.
Your employer doesn’t actually own any hammers, they rent them from OpenHammer (which rents closed-source hammers). OpenHammer bills your employer every time you pick up the hammer, whether you do anything useful with it or not.
Your employer just looks at their bill at the end of the month, and they offer a round of applause and a pat on the back for their most productive employees… you know, the ones that picked up the hammer a bunch of times?
So this “tool” just picks up a hammer a bunch of times, not doing anything useful with it or anything. It’s mostly meming on how stupid a lot of employers are getting hyped on AI.
Your example isn’t even far fetched. A friend of mine who worked in construction knew a crew of framers whose employer paid them based on the number of nails they used. Of course, they did exactly what their dumb employer should have expected them to do: Use way more nails than needed. Any place a nail would fit, they added one. He said listening to the crew work was literally a non-stop rapid fire thunk thunk thunk thunk as at least one of them was busy emptying his nailgun into the work at any given time. No idea how they stayed in business, but people giving dumb incentives is nothing new.
Some short-sighted companies are evaluating employees on AI use, with more being better. This script sends tons of requests to one of the main LLMs, allowing you to appear to use AI a ton. It has the side benefit of costing your employer a ton of money.
Another angle: the cost of AI is highly subsidized. Every use costs the AI company considerably more than they’re charging (read Ed Zitron’s commentary on this). Example: A June 2026 SemiAnalysis report shows that a $200/mo Claude subscription can, when maxed out, cost Anthropic $8000/mo in tokens. Therefore, one way to harm AI companies is to max out one’s subscription.
i wonder if thats calculated/priced in the water/electricity usage too, or hazardous pollutants.
Haha i love it.
I was confused because I misread it as a way to get a job. Like it messed up thierhumanAI Resources software.
eli5: you use the tool more often, so you must work more, since ai is seen as amplifying the work output
Seems like a waste of water.
Burn baby burn! Diss-code inferno! 🎶
