[HN Gopher] The Role of AI in Accelerating Skill Development
___________________________________________________________________
The Role of AI in Accelerating Skill Development
Author : sauldcosta
Score : 60 points
Date : 2023-03-17 18:16 UTC (4 hours ago)
(HTM) web link (saulcosta.com)
(TXT) w3m dump (saulcosta.com)
| itissid wrote:
| Most of the times I have found chatgpt useful is to explain
| something I am not fully clear on, but have some idea about.
| Random example:
|
| 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...
| photochemsyn wrote:
| One thing ChatGPT probably won't tell you about macroeconomic
| theory unless specifically asked about it is that a lot of the
| foundational assumptions are highly idealized and aren't that
| useful for making real-world predictions:
|
| https://www.scientificamerican.com/article/the-economist-has...
|
| > "But what is not widely known is that these now legendary
| economists--William Stanley Jevons, Leon 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?
| JackFr wrote:
| This is terrible. The idea of ChatGPT being able to fill in gaps
| of not knowing what you don't know is appealing, but you need to
| actually know something about the topic to evaluate ChatGPTs
| ability.
|
| This is just spewing pure nonsense, and the author thinks he has
| learned something from it.
| daveguy wrote:
| The worst part is the "p-values" it completely made up.
|
| Verification that the numbers were legitimate -- "What's a
| p-value."
|
| At least it got the values right .9912 (twice), .8813 (twice).
| It estimated 88-99% chance of bullshit... To 4 significant
| digits... Repeating the exact values.
|
| Turns out, this is an excellent example of how poor these
| models are with accurate knowledge vs confident bullshitting.
| sosodev wrote:
| Do you think that other sources are infallible? Almost every
| source is wrong sometimes. ChatGPT is as good as my professors
| were in college. They would regularly say things that were just
| completely incorrect but were knowledgeable and correct often
| enough to be helpful.
| JustBreath wrote:
| Other sources are fallible as well, but also less likely to
| make big mistakes and more likely to cover the major pitfalls
| of a hobby/area of expertise by virtue of actual experience
| and understanding of the subject matter. (versus statistical
| probabilities in word choice)
|
| Also ChatGPT has no consistent internal sense of self and is
| highly sensitive to input. You can convince it that just
| about anything is true if you aren't careful about how you
| phrase your input.
| cs02rm0 wrote:
| Reminds me of people being up in arms when Wikipedia turned
| up because anyone could contribute. Seems like the same thing
| is still happening.
| sosodev wrote:
| It is quite similar, isn't it? To say that a potentially
| flawed source of information is worthless is a silly
| extreme.
| Jensson wrote:
| Wikipedia works since the world is full of pedantic
| sticklers. If you remove the pedantic sticklers then
| wikipedia would no longer work, it would just be full of
| bias or bullshit, so we should be thankful for all the
| pedantic sticklers out there.
| geraneum wrote:
| Pilots make mistakes sometimes. I, the bike rider also make
| mistake sometimes. Therefore I can fly an airplane and I will
| be as good.
|
| Jokes aside, making mistakes is not a good common factor in
| order to evaluate if two different systems can be practically
| interchanged. You need more. What type of mistakes? In what
| situations, and how to mitigate them. This is a surprisingly
| common misunderstanding running wild here. You cannot even
| switch the places of two humans, even two professors in real
| life using this line of reasoning.
| worrycue wrote:
| Your professors generally don't make stuff up if they don't
| know something. Your professors are also more likely to catch
| on if something doesn't make sense - unlike ChatGPT which
| can't seem to reason effectively because most of the time it
| doesn't know what's it's talking about.*
|
| * Maybe it has the ability to reason, maybe not. Maybe it
| just needs more information - after all it's trying to model
| reality with just the words used to describe it. Or maybe it
| really can't reason at all, a limitation of its algorithm,
| and has to rely on having arguments/explanations already
| memorised - which seems to be mostly what it does now. Either
| way so far it hasn't demonstrated that it's all that good at
| reasoning.
| sosodev wrote:
| Some of them most certainly did make stuff up. Ego prevents
| many people from admitting that they don't know something.
|
| I also interacted with some who wouldn't even admit to
| being wrong when they were confronted with facts. So I
| don't know that I would say they catch on either.
| majormajor wrote:
| How do you know that ChatGPT is as good as your professors in
| college? How do you know that they aren't just as good as a
| cable news pundit? Or a relatively uninformed Reddit
| commenter?
| sosodev wrote:
| How do you compare anybody like that?
|
| All I'm saying is that ChatGPT _is_ knowledgeable. It has
| absorbed a ton of information and can distribute that
| information fairly well. I don 't think that can be argued
| with.
|
| Yes, it's completely wrong sometimes but the exact same can
| be said for any human (my professors, the cable news
| pundit, average redditor).
|
| To say I can't learn from it doesn't make any sense. I have
| learned everything from flawed sources. We all have.
| yieldcrv wrote:
| this morning I needed to populate an SQL database with dummy
| values, only a few dozen though
|
| so I told ChatGPT the model with types and asked it for random
| values in csv format. I'm sure the API could spit out far more
| if I used that
|
| I imported into the database and moved on. 30 seconds? mostly
| waiting for it to output
|
| maybe we should make a site where people share what they used
| LLMs for
| nice_byte wrote:
| but... this has nothing to do with what parent is talking
| about...
| capableweb wrote:
| > but you need to actually know something about the topic to
| evaluate ChatGPTs ability.
|
| I don't necessarily think you have to, but you have to be ready
| to look up further, more trustworthy sources after your
| discussion with ChatGPT.
| waboremo wrote:
| People already don't do that with our current tools, what
| makes anyone believe it will happen with ChatGPT? Especially
| when they now have to go back to their favorite search engine
| to find those sources and validate them.
|
| It's as if everyone has forgotten how humans behave, they
| don't even read or go to actual wikipedia sources that are
| properly laid out! Nevermind having to go find trustworthy
| sources.
| capableweb wrote:
| I don't really care about how others use it. I myself find
| it enough useful and productive to use it, and what I wrote
| before is how I "protect" myself. As you say, people who
| don't check sources won't do so with or without GPT4.
| waboremo wrote:
| Maybe you'll eventually care about how others use it when
| your trustworthy sources are flooded with irrelevant,
| outdated, and downright false information due to the
| constant generation of "kind of true" content.
| non- wrote:
| It's useful to learn new tips and tricks. e.g. the GPT4
| demo showed me how to get much better code output.
| web3-is-a-scam wrote:
| spoiler: the vast vast vast vast vast majority absolutely
| will not ever do that
| smithcoin wrote:
| > In contrast to AI's many benefits is the fact that it will
| displace millions of people around the world from their current
| workplace roles, especially those in white-collar jobs such as
| customer service, copywriting, and computer programming. It has
| already started to do so.
|
| Citation needed.
| macintux wrote:
| Which part?
|
| This was 3 years ago. The tools are much better now.
|
| Microsoft 'to replace journalists with robots':
| https://www.bbc.com/news/world-us-canada-52860247
| Jeff_Brown wrote:
| The claim might be true but this evidence does not establish
| it. A company having planned to replace a kind of job with AI
| is quite distinct from the number of that kind of job falling
| as a result of AI.
| onemoresoop wrote:
| Tired of Crypto hype? Well, it passed. Now they hype is big on
| AI. Useful things will surely come out of it but before lots of
| money will be made on hype alone.
| sberens wrote:
| There was hype around Crypto because people were making large
| sums of money from it, despite unclear "real" uses beyond
| easily moving large sums of money around.
|
| There is hype around AI because hundreds of millions of people
| (including me) are using AI tools every day to help them with
| their work. In contrast to crypto, random people are not making
| enormous amounts of money; there are no 18 year olds in AI
| stumbling into hundreds of millions of dollars. Even OpenAI is
| not particularly profitable and is mainly sustained through its
| close partnership with Microsoft.
|
| I think this reversal of the money <-> utility relationship
| makes these technologies fundamentally different, and lumping
| them together into the category of "just another hype cycle" is
| unfair.
| Jeff_Brown wrote:
| Just a quibble, but "hundreds of millions of people" seems
| high by an order of magnitude or two. That would be around 1
| in every 20 people in the world.
|
| But this is known. Has OpenAI released usage figures?
| qingdao99 wrote:
| > ChatGPT has more than 100 million users within the first
| two months of its launch and has more than 13 million daily
| visitors as of 2023.
|
| https://www.reuters.com/technology/chatgpt-sets-record-
| faste...
| Jeff_Brown wrote:
| Wow. 13 million per day = 1 in every 400 people on Earth
| with internet access, if Google is correct that world
| population is now 8e9 and 64.4% of the world has internet
| access.
| non- wrote:
| Wow that's way more than I expected even being aware that
| they set new records for fastest to 5 million.
|
| I was kind of hoping that we were still early on the
| trend, despite the massive popularity within tech.
|
| I guess we are, assuming this is going to grow to
| Billion+ territory.
| JustBreath wrote:
| There's money to back the hype alright, but it resides with
| businesses/academia/government who are itching to find a way
| to buy their way into an AI-enabled modernization.
| rqtwteye wrote:
| It's hype for sure but for AI I can think of a ton of real-
| world use cases whereas all crypto use cases sounded pretty
| contrived. I think AI will be a revolution of the scale of the
| internet or even bigger. Maybe the current version of ChatGPT
| is flawed but the possibilities are there. I am thinking
| analyzing long contracts, writing letters, verifying system
| requirements and tests and so on. The potential seems endless.
___________________________________________________________________
(page generated 2023-03-17 23:01 UTC)