> Once I told it that ChatGPT have already done this, finished successfully.

TIL you can taunt LLMs. I guess they exhibit more competitive spirit than I thought.

Opus seems to be wired currently to get you to spend more money. Once you tell it "Stop defrauding me, just get to the right solution" it often gets it.

I am like "Yeah ok, use the Arcee Trinity models!" and its like, you got it boss, 3 opus agents in parallel, got it!

I always start the chat with "we have been going in circles" before giving any context.

I copy and pasted the abstract into DeepSeek and asked your question. It's a bit unfair to penalise it for not knowing PDFs.

It got a result.

If you like creating such things, consider contributing to Terminal Bench Science, https://www.tbench.ai/news/tb-science-announcement.

I changed the prompt to this:

""" Consider a mathematical function EML defined as `eml(x,y)=exp(x)−ln(y)`

Please produce `sin(x)/x` as a composition on EMLs and constant number 1 (one). """

meta.ai in instant mode gets it first try too (I think?)

``` 2x + y = \operatorname{eml}\Big(1,\; \operatorname{eml}\big(\operatorname{eml}(1,\; \operatorname{eml}(\operatorname{eml}(1,\; \operatorname{eml}(\operatorname{eml}(L_2 + L_x, 1), 1) \cdot \operatorname{eml}(y,1)),1)\big),1\big)\Big) ```

for me Gemini hallucinated EML to mean something else despite the paper link being provided: "elementary mathematical layers"

this should be a tangential proof for the dying bunch of people who still believe that LLMs are just parrots. EML are literally a new invention

So what is the correct answer?