by sauldcosta on 3/17/23, 6:16 PM with 51 comments
by JackFr on 3/17/23, 7:27 PM
This is just spewing pure nonsense, and the author thinks he has learned something from it.
by smithcoin on 3/17/23, 7:30 PM
Citation needed.
by onemoresoop on 3/17/23, 7:34 PM
by itissid on 3/17/23, 9:04 PM
I read from this[1] source that CLO transactions(and hence cashflows) are "arbitrage". And I wanted to understand what is the exact arbitrage.
------------------------------ Prompt: Do you know what is Arbitrage CLOs in this context?
ChatGPT: Yes, I can explain what Arbitrage CLOs are in the context of Collateralized Loan Obligations (CLOs).
Arbitrage CLOs are a type of CLO that is structured to take advantage of differences in the yields of the loans included in the CLO's underlying asset pool. The goal of an Arbitrage CLO is to generate a higher yield than the cost of financing the CLO by purchasing the underlying loans at a lower cost and then securitizing them into higher-yielding CLO securities.
In an Arbitrage CLO, the issuer will purchase a pool of loans at a discount and then securitize them into several tranches of securities with different levels of risk and return. The securities are then sold to investors at a higher price than the cost of the underlying loans, generating a profit for the issuer.
The difference between the yield on the underlying loans and the yield on the CLO securities is known as the "spread," and it represents the profit that the issuer earns from the CLO. In an Arbitrage CLO, the spread is typically larger for the more junior tranches of securities, which offer higher yields but also carry higher risk.
Arbitrage CLOs can be an attractive investment for investors who are looking for high-yield, high-risk investments. However, they can also be volatile and carry significant risk, particularly in periods of economic stress or market volatility. As with any investment, it is important to carefully consider the risks and potential rewards before investing in an Arbitrage CLO.
-----------------------------------------
So, I learn't(or confirmed my intuition) that the arbitrage occurs because of discount on loans.
[1] https://content.naic.org/sites/default/files/capital-markets...
by photochemsyn on 3/17/23, 9:30 PM
https://www.scientificamerican.com/article/the-economist-has...
> "But what is not widely known is that these now legendary economists—William Stanley Jevons, Léon Walras, Maria Edgeworth and Vilfredo Pareto—developed their theories by adapting equations from 19th-century physics that eventually became obsolete."
I'd probably trust ChatGPT more on elucidating the history of the development of macroeconomic theory then on applications of the theory to real-world problems, but that goes for the working professionals in the field as well, with all their rosy predictions of the benefits of NAFTA to the working public in the 1990s, or their predictions of the benefits of financial deregulation in the early 2000s prior to the 2008 Recession, and so on.
E.g. ChatGPT claims American academic institutions adopted macroeconomic theory with Milton Friedman at Chicago and Alvin Hansen at Harvard, and this was preceded by development in the 1920s at the National Bureau of Economic Research and in the 1930s with the Cowles Commission. If you ask it what role the above four individuals in the quote played in the development of macroeconomic theory, it gives illuminating answers on utility, general equilibrium, indifference curves, and Pareto efficiency (which, ChatGPT claims strongly, is not zero-sum game thinking). This all seems fairly accurate based on other sources, except that the relationship between game theory and Pareto efficiency seems fairly contentious.
Also, here's a good question to ask it in the context of the desirability of optimizing Pareto efficiency:
"Has macroeconomic theory ever been criticized on teleological grounds?"
Generally, this is probably not the best subject to give to ChatGPT as a quantitative test. Maybe try it out with something more concrete, like how to use gravitational assist (aka 'slingshot') to send a spacecraft to Jupiter or Saturn, and see how explicit it can get in terms of a launch trajectory?
by f0ld on 3/18/23, 1:12 AM
by falsaberN1 on 3/18/23, 1:46 AM
Long answer, following my latest involvement with AI stuff:
I haven't really played that much with text models, ChatGPT and such, but I can kind of relate to this when Stable Diffusion is involved. I'm a fairly competent artist, and I enjoy drawing both elaborate art pieces and doodling random stuff when bored or when someone says something funny in my socials, and despite the hate of many of my peers, I picked it up and got my own local instance to have fun with. This thing has fully revolutionized my world as an artist. It's only been like half a year and I don't think I have drawn so much since high school, specially during tough work seasons where I'd normally be busy and too tired to draw in my free time. You can say that every year my quality goes up by a roughly equivalent amount, and this year I'm already outpacing myself.
I don't know, I can't quite explain it in simple terms, but I'd wager it's both the stimulus of seeing art of topics and characters that would normally take months or years between a single new image, and the AI failing at certain elements often (hands, fine details and decorations, eyes, etc...) making you more aware of those elements and thus becoming more mindful of them when drawing, even at a somewhat subconscious level. Not to mention when the AI does something hilarious and you kinda make it a thing or draw it "for real" from scratch.
And, thinking about it, there's also some ancillary art exercises the AI has gotten me into. Editing images (for training or "this generated image will be 100% perfect if I redraw this part myself" cases, which makes you learn a lot because of the huge amount of different styles this can generate. Gotta learn to recreate that shading style on the spot!), stuff like ControlNet accepting quick sketches as input, and wanting to duplicate some of the more fascinating things the AI generates. Training models can become a full "art project" given enough love and care and manual art supply. And this also incentivizes to be very clear and tidy for the training to go well. And all of this becomes practice and experience.
Being able to generate really decent images in a few seconds is never going to take away my fun or motivations when drawing, and it's opening new paths to have fun with art, too. In that regard, and finally tying with the thread's content, if the AI has managed to not only help me improve but make me even more active in art, I'm sure it can have similar effects in other fields as well. A writer can easily improve, learning from the terrible goofs, hilarious twists and occasional "getting it just right" moments the text models provide. I can see the same thing happening in areas like music or whatever comes next. An observant and motivated use can turn a ML system into a goldmine of custom examples, and at a ridiculous fast pace, without tiring and on demand!.
And it's fun to tinker with the code, too.