[HN Gopher] Creating personalised data stories with GPT-3
       ___________________________________________________________________
        
       Creating personalised data stories with GPT-3
        
       Author : ColinEberhardt
       Score  : 29 points
       Date   : 2021-12-08 09:05 UTC (1 days ago)
        
 (HTM) web link (blog.scottlogic.com)
 (TXT) w3m dump (blog.scottlogic.com)
        
       | thewarrior wrote:
       | Do this for peoples stock portfolios and you have a good startup
       | idea right there.
       | 
       | Or you could digest financial, health and content consumption
       | data to create a personalized report with action items.
       | 
       | Very promising.
        
         | elikoga wrote:
         | I agree, that also looks like a great use case. I'm sure there
         | are many more to come.
         | 
         | One thing I love about GPT-3 is that it uses the same common
         | language for the "data people" and the "non-data" people. The
         | same description works for both.
         | 
         | This makes it so easy to explain what you are doing. I think
         | that is a huge advantage over existing text generation methods.
        
       | cryptoz wrote:
       | A good article, I appreciate all the discussion on prompts too.
       | However the author is a bit too underestimating of the language
       | model and math:
       | 
       | > GPT-3 is quick to learn that the narratives should include
       | these comparisons, but often gets the maths wrong:
       | 
       | > > During these runs he has climbed 62,599 feet, that's the
       | equivalent of climbing Mount Everest six times (but a bit less
       | steep)
       | 
       | > Everest is ~29,000 feet, so this runner has climbed Everest
       | roughly twice.
       | 
       | I think it's the author here who gets the math wrong. An Everest
       | climb is closer to 10,000 feet, making the GPT-3 math alarmingly
       | accurate.
        
         | jeanloolz wrote:
         | Mount Everest, as far as I know is near 8850 meters high, which
         | in feet is probably around 30000. The article snippets you took
         | seem right to me, the author math checks out.
        
           | cryptoz wrote:
           | Right but you can't climb that. The author's math ignores the
           | real context of climbing and uses a google search for the
           | math. But no climber can climb the full altitude due to the
           | physical geography. There's nobody that can relate to
           | climbing that altitude on one mountain because the physical
           | ground isn't like that.
           | 
           | I guess what I'm saying is the AI is showing better
           | understanding of climbing context than the author is giving
           | credit for.
        
             | joe_the_user wrote:
             | It's implausible that GTP-3 wrote that because it knew the
             | actual amount of climbing involve in an Everest ascent and
             | tosses it without comment in a way that would look wrong to
             | most people who read it.
             | 
             | It's far more likely that the program cobbled together a
             | variety of factoids and so got it's wrong-sounding
             | statement in the same way it makes many other clearly wrong
             | or illogical statements.
        
             | peab wrote:
             | Yes, according to this the elevation gains are ~3500m which
             | is ~11,000 feet: https://www.strava.com/challenges/Strava-
             | Climbing-Challenge-...
        
       | savant_penguin wrote:
       | To anyone who knows about the subject, what is the best gpt-like
       | model you can still run in a laptop? (With about 16gb of ram, or
       | 3gb-8gb of vram)
        
         | dyndos wrote:
         | GPT-2 is the most recent available from OpenAI. Otherwise you'd
         | need to look at EleutherAI's GPT-Neo which comes in various
         | sizes.
        
       ___________________________________________________________________
       (page generated 2021-12-09 23:01 UTC)