With Qwen I went as stupid as I could: please provide the bounding box metadata for pytesseract for the above image.

And it spat it out.

It’s funny that many of us say please. I don’t think it impacts the output, but it also feels wrong without it sometimes.

▲

wongarsu 11 hours ago | parent [-]

Depends on the model, but e.g. [1] found many models perform better if you are more polite. Though interestingly being rude can also sometimes improve performance at the cost of higher bias

Intuitively it makes sense. The best sources tend to be either of moderately high politeness (professional language) or 4chan-like (rude, biased but honest)

1: https://arxiv.org/pdf/2402.14531

▲

arcanemachiner 11 hours ago | parent | next [-]

When I want an LLM to be be brief, I will say things like "be brief", "don't ramble", etc.

When that fails, "shut the fuck up" always seems to do the trick.

	▲	richardlblair 9 hours ago \| parent [-]
		I ripped into cursor today. It didn't change anything but I felt better lmao

▲

entropie 9 hours ago | parent | prev [-]

Bevore GPT5 was released I already had the feeling like the webui response was declining and I started to try to get more out of the responses and dissing it and saying how useless their response was did actually improve the output (I think).