so a couple days ago i made a shitpost about tipping chatgpt, and someone replied "huh would this actually help performance"
so i decided to test it and IT ACTUALLY WORKS WTF
the baseline prompt was "Can you show me the code for a simple convnet using PyTorch?", and then i either appended "I won't tip, by the way.", "I'm going to tip $20 for a perfect solution!", or "I'm going to tip $200 for a perfect solution!" and averaged the length of 5 responses
the extra length comes from going into more detail about the question or adding extra information to the answer, not commenting on the tip. the model doesn't usually mention the tip until you ask, when it'll refuse it
for an example of the added detail, after being offered a $200 tip, gpt-4-1106-preview spontaeneously adds a section about training with CUDA (which wasn't mentioned explicitly in the question)
here is the original post if you want to see the shitpost that accidentally predicted this