Working with fine-tuning based on stackexchange answers

I had an idea for a “writer’s question answerer” that could address all the odd questions people ask in writing based subreddits. I was going to use the writing stackexchange solely but decided to throw in “philosophy” and “puzzles” too. I had yet to find a good metaphor / wordplay / simile dataset but the “puzzles” stackexchange appears to be such a source.

What is an analogy for the stock market?

If you had to describe the stock market in poetic pentameter, how would you do it?

Part of it is this:I’m the needle in the haystack,Find me if you canWhen you see the needle deep withinA hint of what might be central thoughtLess obvious things, to focus you hereI’m the key to the universe;Show me the right to runI seek out what you seek outLook inside your mind, I’m to be foundWhat do I mean by stock market?The universe of trading knowledge. (More or less)The universe has its own mind; (Less or more)You can’t see me, you must think I’m what? (There isn’t anything, so I’m the stock market.)I’m the core to your fortune,And I’m central to two things,Everything you do you try to rely on me.The universe is much bigger than galaxiesAnd life is part of everything;You can’t just use your headsYou need my mind as wellInside you dwellersInside outAnd I give you abilityTo act without delayOr inside your headsAn alternative interpretation would be that one can not digest or digest to much, so the universe has to send these hunger pains into the universe core to get things going again. I figure it out, but you can play around with it :slight_smile:

The reason a poetic name for a stock market is easy to remember is that stock markets are mostly about bargaining. If a businessman is going to be successful he has to convince a buyer that he is offering less than what they want, and more than what they expect. In this sense poetry is about negotiation. So apart from stopping talking nonsense, a good description of a stock market might be: “where businessmen negotiate for better offers.” Or perhaps "where customers bargain for better services."In response to second answer, I personally find one of the most popular names that is used for a lot of slightly different markets on Stock Exchange Online (“XE”) apropos: “exchange”. The idea here being that stock markets are where buyers and sellers come together to trade items/services/money. This is also a metaphor for how markets function. The world’s marketplaces don’t just exchange physical items between buyer and seller, but rather they exchange ideas - kind of like stock markets except for more tangible things. So from there I would suggest the name of good old “Xstreet” connecting buyers and sellers from all over the world.In answer 3, personally I find that there is nothing particularly special about stock markets compared with other centralized exchanges for buying and selling (say). Indeed, the old Chinese saying “buy low and sell high” was originally applied to people trying to make trades on local markets instead of larger centralized

One more that I liked was (I actually like digressions sometimes):

What do you call a machine learning model that can answer any question?

I thought that a “generalized question answerer” sounded a bit silly lol.

A GQA can answer any question which can be reduced to an answerable statement - e.g., “Does this object contain a ball?” The question Then the statement is true if the answer is yes, and if false if the answer is no.is more restrictive than "Does this object contain a ball?"The questionThen the statement is true if the answer is yes.is more restrictive than “Does this object contain a ball?”. This is one of the reasons why you’re unlikely to find an actual GQA in day-to-day applications, although hyper-contextual GQAs exist. A ‘knowledge’ base of this type would be extremely powerful, of course - it would also require major shifts in current AI practice. This might be envisaged as involving large databases of common questions and answers indexed on queries, for example. A modern GQA would probably need to be able to understand context and so on.A link to an answer elsewhere in the same answer forum means that “context” may be required - e.g., “Can this object be used as a sphere?” or “Can this be an ultra-violet light?” A related question may be "We know that the moon is made of green cheese, does this object contain cheese?"But, of course, any given answer can be rephrased. For example, “Does this object contain cheese?” Can be paraphrased as “Do these imaginary properties exist?”. Answering these questions might involve constructing diagrams showing what comes into existence when specific conditions are met, e.g., related related to the rephrasing.So maybe instead you could say that it’s a model that can derive additional knowledge by construing statements into formulae that are then evaluated for truth or falsehood. An example that comes to mind is something like this: You are then offered a meal at Joe’s diner which contains ham, eggs, bread and lard. This does not contain cheese. Right away you can see at least two problems with this kind of rule-based approach - the first being that you might have ordered scrambled eggs with bread but eggs without bread would not be included in the meal!The second problem is that an experienced diner like Joe would probably never use the word “lard”.He (she?) might instead offer such choices as:You are then offered a meal at Joe’s diner which contains ham, eggs, bread and pork fat. This does not contain fat.You are then offered a meal at Joe’s diner which contains ham, eggs, bread and cream spread. This does not contain either pork fat or cream spread.

I am still not sure which format is easiest to read but I put a few on Medium cuz it looks nice, here.

The code’s really simple, here’s that as well!

1 Like