AI summary of arXiv:… the ChatGPT Online version

I tried the same initial question, described here, ie “summarize arXiv:1103.6007”, this time with ChatGPT Online.

The result is the following:

“In the paper “The New Physics of Bird Flight: From Flight Planes to Acrobatics”, the authors explore the physical principles behind bird flight. They discuss how birds are able to generate lift and control their movement in the air, drawing comparisons to the principles of fixed-wing aircraft and helicopters. The paper also highlights the acrobatic maneuvers performed by birds during flight and the underlying mechanisms that enable them. The authors propose a new framework for understanding bird flight based on the interaction between aerodynamic, biomechanical, and neural factors. They believe that this interdisciplinary approach can contribute to the development of advanced flying machines inspired by bird flight.”

Of course that this has nothing to do with arXiv:1103.6007. Moreover I was not able to find any paper titled “The New Physics of Bird Flight: From Flight Planes to Acrobatics”, with google or ddg search!

It’s pure invention, this AI does not even try to locate an arXiv ID, is just useless drivel.

Now, I know that there are services online, to summarize arXiv articles. But they are either demanding a login or are exclusive to chrome.

Why would that be?

The answer, in my opinion, is very simple. Is the same answer as, for example, the one about Open Access: why would the open access research articles should be Gold (ie paid by the authors) or otherwise not recognized as publication? Or even if a technical solution appears for OA, with no cost, is then prosecuted? Because otherwise one major pillar of the society would no longer be controlled.

Now we see, in the making, the phenomenon where these new AI are trained on huge quantities of data but they are unable to process a tiny, tiny quantity of data. Indeed, the collection of all research articles ever written on Earth is tiny compared to what they use to train these AI.

So why? Because, while talent appears more or less evenly distributed, the scientific superiority and access are one of those sensible pillars of the society.

What would it look like if we could trace and compare the genesis of the ideas in research? Can’t be a public, free service, right? Most of research would appear to be badly written drivel, compressible to an even tinier quantity of data which will turn out that is authored by an evenly distributed collection of people.

Am I wrong? Prove me wrong.

Oh, incidentally, I tried also to see what happens when I ask the AI to summarize a piece of genius made text, like the madeleine passage from Proust. Result? Incompressible or turns to bland, tasteless, unsubtle, commercial quality text. For another time.