Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A professor built a chatbot to be his teaching assistant

washingtonpost.com

Post reply on HN
Print view View original

101–110 of 120 posts

Re: A professor built a chatbot to be his teaching assistant

#101

Post by jschwartzi »

SilasX wrote: post #100
Swizec wrote: post #98

Earlier quoted context omitted.

I can get some meaning out of it. If I knew the context, I could get more. May I suggest running it through HemingwayApp[1] yourself and seeing that this particular email is objectively hard to read? Write emails (and internet comments) like the reader is a drunk 7 year old. That's about as much attention as they're giving your email. [1] http://www.hemingwayapp.com/

You're not answering the question. What specifically is hard to understand? Formulas are just heuristics, not some ironclad objective proof of illegibility. Ironically enough, across two comments, you haven't been able to convey such substantiation. You also haven't explained what makes it horrible rather than so-so, which is important, since it's fairly easy to make it worse. You really can't just count words and do…

My lead is like that. When I send him instructions on how to do something, he always asks me to sit with him and walk him through them rather than attempting to follow them and then asking questions if he gets stuck.

Re: A professor built a chatbot to be his teaching assistant

#102

Post by lizzard »

adekok wrote: post #29
collyw wrote: post #25

Rather than inventing sophisticated chat bots, couldn't he have just had a well organised web page? If the question were where is assignment two / when is assignment due. The examples given seem like a "high tech" (possibly unreliable) solution to a low tech problem.

Having written documentation for end users, that will work for only a portion of them. Probably most, which is good. But there are a significant percentage of users who can't (or won't) read documentation. Even they do manage to read it, they don't understand it. For some reason, human interaction works better for those people. They ask a question, and someone copies the answer from the documentation, and pastes it i…

Sometimes this is about having a different learning style. Some people may absorb information better one on one. Tutoring and mentoring can be super helpful.

Another thing you might consider is that there are class and cultural factors to people's expectations about how you get along in life. Person to person conversation and personal relationships are important resources if you are working class or living in poverty.

There is a flip side to culture that disdains just asking, which is that smart people sometimes scramble to find answers independently to any questions because they don't want to reveal their ignorance on a subject. Sometimes just asking is not lazy, it is efficient and results in better collaboration as other people hear the question and realize they don't know, either, and would like to. Or, if no one knows, then you at least know have that information and can work from there.

Re: A professor built a chatbot to be his teaching assistant

#104

Post by dghughes »

ars wrote: post #19

This is the key: > The system is only allowed to answer questions if it calculates that it is 97 percent or more confident in its answer. Knowing when you don't know the answer is something that has been lacking from AI I've seen. Of course the problem is that not all AI has the option of deferring to a human. Anyone know what percent of questions the AI answered, vs redirected?

Anytime I see anything AI related it seems context is the key otherwise answers are all over the place. It's the same for everyday life context seems to be the driver of humans.

Re: A professor built a chatbot to be his teaching assistant

#105

Post by Swizec »

SilasX wrote: post #100
Swizec wrote: post #98

Earlier quoted context omitted.

I can get some meaning out of it. If I knew the context, I could get more. May I suggest running it through HemingwayApp[1] yourself and seeing that this particular email is objectively hard to read? Write emails (and internet comments) like the reader is a drunk 7 year old. That's about as much attention as they're giving your email. [1] http://www.hemingwayapp.com/

You're not answering the question. What specifically is hard to understand? Formulas are just heuristics, not some ironclad objective proof of illegibility. Ironically enough, across two comments, you haven't been able to convey such substantiation. You also haven't explained what makes it horrible rather than so-so, which is important, since it's fairly easy to make it worse. You really can't just count words and do…

Specifically these two sentences are hard to understand:

     Hey the other day you said you said that the downloaded certificate is one factor, so with the password, that's already two factors, and the rotating token would be three.

     But the CTO is confused then -- how was the certificate securely transmitted in the first place, to the point that we can count it as a second factor?
They are complex sentences. This makes them hard to understand.

The email's reading level is at grade 11 on the Flesch-Kincaid scale. [1] Anything above 9 is considered "Fairly difficult to read". Best selling authors tend to score less than 9. A lot less.

You don't need to write emails like you were a best selling author of course. That's silly. But it helps if you write them for the recipient. Don't just word vomit your train of thought.

Here's how I'd write your email (from what I can guess/understand of the situation):

     Hey,

     The other day we talked about auth factors in our app. You said the certificate was one factor.
     Adding the password, that makes two. A rotating token would make three.

     Do we really need the rotating token, then?

     But the CTO is confused: how do we know the certificate transmitted securely? It can't be an auth factor if we're not sure.

     Cheers,
     ~Bla
That said, we have way over-analyzed your email :)

[1] https://en.wikipedia.org/wiki/Flesch%E2%80%93Kincaid_readabi...

[2] https://contently.com/strategist/2015/01/28/this-surprising-...

Re: A professor built a chatbot to be his teaching assistant

#108

Post by morgante »

SilasX wrote: post #100
Swizec wrote: post #98

Earlier quoted context omitted.

I can get some meaning out of it. If I knew the context, I could get more. May I suggest running it through HemingwayApp[1] yourself and seeing that this particular email is objectively hard to read? Write emails (and internet comments) like the reader is a drunk 7 year old. That's about as much attention as they're giving your email. [1] http://www.hemingwayapp.com/

You're not answering the question. What specifically is hard to understand? Formulas are just heuristics, not some ironclad objective proof of illegibility. Ironically enough, across two comments, you haven't been able to convey such substantiation. You also haven't explained what makes it horrible rather than so-so, which is important, since it's fairly easy to make it worse. You really can't just count words and do…

I had to read the email twice to understand it. It's absolutely hard to read.

At a minimum, each sentence is doing too much.

Re: A professor built a chatbot to be his teaching assistant

#109

Post by morgante »

olalonde wrote: post #38
adekok wrote: post #29

Earlier quoted context omitted.

Having written documentation for end users, that will work for only a portion of them. Probably most, which is good. But there are a significant percentage of users who can't (or won't) read documentation. Even they do manage to read it, they don't understand it. For some reason, human interaction works better for those people. They ask a question, and someone copies the answer from the documentation, and pastes it i…

> I would love to know the psychology behind this phenomenon. Laziness. It's usually faster to ask someone a question than to look up the answer. I used to do this on IRC when learning a new programming language and it saved me a lot of time. If you want an even faster answer, you guess the wrong answer and wait for someone to correct you ( https://meta.wikimedia.org/wiki/Cunningham%27s_Law ).

I don't think that fully explains it.

On my school's forum, people routinely ask questions which a simple Google search would have answered.

Yet typing out a question and posting it to a forum is a lot more work than searching on Google. I'd think the lazy response would be to stick to Google.

Re: A professor built a chatbot to be his teaching assistant

#110

Post by Coding_Cat »

tfm wrote: post #11
lordnacho wrote: post #7

Earlier quoted context omitted.

Hmm, does it count to use things that are not so much to do with the course? For example, if a guy is able to answer questions at all times of day, really fast, they're either an AI or Jon Skeet. Also, real TAs have a life outside of the course. What will an AI say when you ask them whether they enjoyed last night's episode of Game of Thrones?

The software worked remarkably well in this instance because the system was well constrained, and the students weren't on the lookout for it. If they do start quizzing their new unseen TA (Dr Colin V Olutionalnet) on random trivia it could presumably deflect the query or have a few canards pre-programmed.

But likewise, if I were a TA for that course I'd probably try to act like a bot just to confuse the students.
Post reply on HN