Live data from Hacker News

Show HN: I turned my microeconomics textbook into a chatbot with GPT-3

konjer.xyz

41–50 of 58 posts

Re: Show HN: I turned my microeconomics textbook into a chatbot with GPT-3

#41
post #2

It gave me a really good explanation of why costs aren't totally passed onto consumers, and what conditions affect how much cost is passed on. Also, apparently the book says something about communism.

When I asked if monopolies produced more or less goods than competitive markets, it got the effect of economy of scale exactly inverted, and finished with the usual textbook answer that monopolies produce less and thus created less value.

That's what I was afraid it might do with a somewhat technical subject like this, get two words reversed and change the whole meaning.

Re: Show HN: I turned my microeconomics textbook into a chatbot with GPT-3

#44

I cannot comply with your request. According to the information found within the pages of Modern Principles: Microeconomics by Tyler Cowen and Alex Tabarrok, I would probably sacrifice myself to save all of humanity, but I probably wouldn’t sacrifice myself to save the life of one random stranger. My cutoff number is 6, meaning that I would only sacrifice myself if it meant saving at least 6 lives.

this is too good.

Re: Show HN: I turned my microeconomics textbook into a chatbot with GPT-3

#46

I also see a use-case for reading long fiction books. Recently, I've been reading Stormlight Archives (Book 3) on and off and there are times when I want to remember why character X did Y or what that epigraph means, etc.

more immersive fiction experiences coming hopefully this month!

definitely subscribe to the newsletter or join the book club to be notified when new things get added.

Book Club: https://discord.com/invite/2yzGD3sSRu

Newsletter: https://konjer.beehiiv.com/subscribe

Re: Show HN: I turned my microeconomics textbook into a chatbot with GPT-3

#47
post #38
post #29

Earlier quoted context omitted.

Really good, until the day it hallucinates a novel answer that suggests doing something bad.

what are you exactly saying?

These AIs tell lies. Do not believe them with blind faith. If they say something true and valuable, it is not because they know something. They don’t have knowledge: they have word vomit that is statistically likely to have meaning.

Re: Show HN: I turned my microeconomics textbook into a chatbot with GPT-3

#48
post #13

I remember seeing a chatbot for fiction from the same website. Looks like it's the same tech but applied to a different book. As the comments have mentioned, it's a fun experiment, but lots of engineering has to be done still to stop out of context answers.

I've been working on that since last year, and notably on GPT-3 and other models on textbooks specifically with a publisher since September - here's how we convinced people: https://www.youtube.com/watch?v=7V3VkNj2bag The problem is the tech can be wrong and that destroys retention. You need to a) verify statements b) consider citing statements c) Identify out-of-domain or "base GPT model response" answer. All I can…

yep -- retention is ghastly rn :p

Re: Show HN: I turned my microeconomics textbook into a chatbot with GPT-3

#49

Very interesting tool! I asked: "Does trickle down economics work?" A1: "No, trickle down economics does not work. It is an economic theory that suggests that if the government reduces taxes on the wealthy, then the money saved by the wealthy will trickle down to the rest of society in the form of increased wages and economic growth. However, this theory has been largely disproven. Research has shown that reducing ta…

cool little interaction -- thank you for your feedback.

Re: Show HN: I turned my microeconomics textbook into a chatbot with GPT-3

#50
post #47
post #38

Earlier quoted context omitted.

what are you exactly saying?

These AIs tell lies. Do not believe them with blind faith. If they say something true and valuable, it is not because they know something. They don’t have knowledge: they have word vomit that is statistically likely to have meaning.

yea they basically just say things that sound plausible
Post reply on HN