OpenAI GPT-3: Initial Impressions

So, ChatGPT is at capacity right now, and I'm sure not going to sit here and hit refresh every few seconds to try to get in. So I went to https://beta.openai.com/examples and tried a few.

My impressions: disappointing given all the hype, but if I hadn't seen the hype, I would be reasonably impressed.

[UPDATE: I've since gotten into the real ChatGPT, and I must say it is more impressive than the sandbox I played with in this post. The sandbox is based on GPT-3, while ChatGPT is GPT-3.5.]

In the following examples, I am including output from OpenAI's GPT-3 model. In accordance with OpenAI's wishes, my name is Steve Ford, and the text shown in green is generated by an AI.

Analogy maker

My entry is first, followed by the AI response in green.

Get the logic right, then optimize.

It's like building a house: first make sure the foundation is solid, then make it look nice.

Not bad.

Do unto others as you would have them do unto you.

It's like a golden rule of giving and receiving; treat others as you would like to be treated.

Um, I don't think you can use a definition as an analogy. The point of an analogy is to improve understanding of a concept by re-structuring it in different terms that the reader might be more familiar with.

Look out for number one.

It's like putting on your own oxygen mask before helping others on an airplane.

Impressively good and bad. Yes, it kind of understood what the phrase means, but it also completely misses the essence of the phrase. "Watch out for number one" is all about being selfish (Collins dictionary says, "If you are looking out for number one, you are thinking of yourself rather than considering other people"), whereas the analogy is about doing something that might seem selfish at first glance, but is actually in support of generosity and the greater good.

Pro tip: don't use GPT-3 to learn the meaning of idioms.

Do unto others ... and then split Give a hand to those in need ... and then walk away.

This one might not be fair; I wonder how many under-50-year-olds would get that reference. Anyway, the analogy is the exact opposite of the original.

Pro tip: don't use GPT-3 to learn about 50-year-old memes.

There are other example applications that I would like to play with, but who has time for that? Over time, I'll probably have more to say about AI.

Invert the Meaning

I took the analog maker settings and changed the command (or whatever that first line is called) to "Invert the meaning:".

Time flies like an arrow.

Time stands still like a rock.

Not idiomatic, but impressive.

Smoking is bad for you.

Not smoking is bad for you.

Yep, it will lie if you tell it to.

Write an Essay

Took the analog maker settings and changed the command to "Write an essay:"

Why structured programming is bad.

Structured programming is a programming paradigm that relies on breaking down a program into smaller, manageable parts. It is a popular approach to programming because it is easy to understand and can be used to create complex programs. However, there are a number of drawbacks to structured programming that can make it a less than ideal choice for certain projects.

The first issue with structured programming is that it can be difficult to maintain. Because the code is broken down into smaller parts, it can be difficult to keep track of how the parts fit together. This can lead to bugs and errors that can be difficult to debug. Additionally, if changes need to be made to the program, it can be difficult to make sure that all the parts are updated correctly.

Another issue with structured programming is that it can be inflexible. Structured programming relies on a set of predetermined rules and structures, which can limit the options for solving a problem. If a programmer needs to come up with a creative solution, structured programming may not be the best choice.

Finally, structured programming can be slow. The small parts of a program can take a long time to process, especially if there are a lot of them. This can lead to programs that take a long time to run, which can be a problem for projects that require fast results.

In conclusion, structured programming can be a useful approach for certain projects, but it is not without its drawbacks. It can be difficult to maintain, inflexible, and slow. For projects that require creative solutions or fast results, it may be better to use an alternative approach.

Global STAC Live

I normally don't do product or vendor shilling on this blog. But I've always liked Peter Lankford at STAC, and I think he did a good job with this video:

www.STACresearch.com/spring2020

Yes, it's a funny advertisement, but instead of being just plain funny, it's actually pretty clever. And I don't just mean the jokes.

The Coronavirus has really disrupted professional conferences and events. Many are postponed, some are just plain cancelled. I assumed that STAC would be a casualty, but Peter is trying to make lemonade by making his 2020 summit virtual.

Now it's not like that has never been done before. Zoom has made quite a name for itself by saving the business meeting. (In fact, many meetings that used to be simple phone conferences have mysteriously and inexplicably drifted into Zoom meetings, I'm not sure why.)

So when I first heard that the 2020 summit was going virtual, I was like ho-hum ... another endless series of Zoom presentations. And it got me to thinking, what was going to be lost? The sales-oriented participants will of course miss glad-handing prospective customers. But what about engineers like me?

We'll miss getting together with our smart friends and colleagues that we haven't seen for a while, and maybe being introduced to their smart friends and colleagues for interesting conversation, war stories, and maybe even the occasional brilliant technical insight. Not going to get any of that out of a zoom presentation.

But Peter's video suggests that he was fully aware of that drawback, and he is experimenting with approaches to address it. I'm skeptical that I will be blown away by it, but I'm intrigued enough to give it a go. And whether it turns out revolutionary, or just another chat room, I respect Peter for effort.

Plus, I  just plain like the ad. :-)

UPDATE: June 3

At the end of day 2, I can safely say that the STAC Live event was well done. The speakers did a good job of dealing with the new format, and there were very few technical glitches. The system seemed to scale well.

In particular, it is nice to be able to replay sessions that you missed (or just couldn't pay attention to) the same afternoon. This is a clear *advantage* to this format as compared to a traditional in-person conference.

The technical content was also very good, but that's not what I want to talk about.

I'm a little sad to report that the social aspect turned out worse than I had hoped. It's not STAC's fault, nor the fault of Ubivent, the technology behind the virtual event. It's the fault of human nature.

When I travel to a venue to attend a function, I am engaged with the event. Yes, I sometimes check email, and will even sometimes hide in a corner to do an important call. But >90% of my time is spent being fully engaged with the people, both in and out of a session. So conversations happen naturally and productively. You get introduced to new people with similar interests. I made a very good friend at a conference a few years ago, just because I was there.

During STAC Live, the chat feature was there, but wasn't used very much. And like all chats, I might type something, and minutes would go by before the response came back. Why? BECAUSE WE'RE ALL BUSY, THAT'S WHY! During an in-person event, we are mostly engaged with our surroundings, but when attending remotely, we are balancing the virtual event with work. And work usually wins. And working from home means there's also family members and pets who need attention.

So even if the event technology were somehow more conducive to socializing, the attendees were not.

So, overall STAC was a good event, better than it had any right to be given the circumstances. And I've already learned some things that I plan to put into practice, so it's been well worth the time. But it being a virtual event does detract something meaningful. And I miss it.

Don't Be a Spreader

Max Brooks PSA about Corona Virus

https://www.youtube.com/watch?v=DthdYTLiqcI

Return of the Wiki

A while ago I migrated from a traditional hosting service to GitHub. One thing I lost in the process was access to a mediawiki installation for a personal Wiki. I like Wikis, and I've missed it ever since.

That is, until I finally looked a little closer at GitHub and saw that they support Wikis! DOH! So now I'm experimenting with it and so far I like it (still very early days). Each Wiki is stored in its own git repo and can be cloned and worked on off-line.

One problem is that they haven't integrated the Wiki repos with the general GitHub software very well, so the GitHub Desktop GUI application can't deal with it. The doc says it does, but the doc lies. You have to use command-line git.

But that's not a big problem. One of the reasons I like Wikis is a low-barrier to updating. And having to edit files, write them out, and then do the git commands to update is *not* low-barrier. So my usage will be almost exclusively via the web.

But it's nice to know that if my Wiki grows large, I can run sed scripts on the files to make global changes if I want.

Anyway, THANKS GitHub!

Goodby my Wiki

This post is a little late in coming as I made the change earlier this year.

I used to use a hosting service, suso.com,  for my main website and email.  It ran a message board I built using Perl, and it also ran a older version of wikimedia for a personal wiki.  But the service cost a fair amount, and neither the message board nor the wiki was being used much.  So to save money, I cancelled it and moved the content to github.

The content is still available at geeky-boy.com, but I dumped the wiki pages to a flat directory.  If I want to edit them, I need to edit the raw HTML.

I somewhat mourn the loss of my wiki.  I like wikis for certain kinds of content.  It is especially powerful for collaborative efforts, particularly for geographically-separated teams.  But even for single-user personal-use, it presents such a low barrier to use.  If I want to update a page, it's just a few button clicks away.  And the update process is easy (assuming minimal use of fancy wiki markup).  And it's easy to see change history, roll back changes, etc.

Contrast this with web pages on github where you have to edit them locally in HTML, check in the changes, and sync with "gh-pages" branch to make them live.  It takes longer, and requires specialized software.  E.g. I can't easily do it from a phone or tablet.

There are "free" wikis out there, but I don't like the ads, and most of them use non-wikimedia software; the few I've tried I haven't liked.

Maybe someday I will try some kind of third-party content management system.  Or maybe I'll write my own wiki software as a fun personal project (maybe do the rendering of the markup in the browser in Javascript).  Or maybe I just don't really need a wiki.  Long ago, I imagined that the blog and the wiki would compliment each other, with content in each referring to content in the other.  Blog for "news", wiki for "content".  But it hasn't worked out that way.

So rest-in-peace wiki.geeky-boy.com.  You were fun while you lasted.

Blog tags

Tags are used to group posts.  If you want to see all of my postings related to, say, "death", just click on the "death" tag and you'll see the list.

I like tags.  It is better than a hierarchical system of organization since a particular item may be associated with multiple points in the hierarchy.  E.g. I might have a post tagged as "coding" and "rants", if I have a rant about some aspect of coding.

[Aside - email clients traditionally use a hierarchical folders.  But gmail (at least the web interface) gives you true tagging.  I like that, but ironically don't use it.]

One complication of tags as an organizational model is that the tags themselves must be organized, especially if the number of tags gets large.  THAT strikes me as something which could be organize into a hierarchy.  I might have a rants tag and a technical tag.  The technical tag might be sub-divided into science and software.  Software might be further subdivided into coding and debugging.  My rant about coding would show up in both the "rants" tag and the "coding" tag.

Alas, this blogging system does not allow for organizing tags hierarchically ... at least not that I know of.  It gives you two views:

• Alphabetical
• Tag cloud

The "tag cloud" is interesting.  It uses different font sizes for the tags, depending on the relative number of postings given that tag.  So rants might be big because I do a lot of ranting, while science might be small because I don't do much blogging about general science.  The tag cloud gives an interesting view into my head even without clicking on any of them since they suggest which topics I feel passionate about (or at least chatty about).

That said, I'm thinking it is more of a novelty than a useful organizational model.  (It's a novelty that I like, which is why I enabled it on this blog.  But it will suffer from the same unwieldiness if I create a lot of tags.)  For large numbers of tags, I'm still leaning towards hierarchical.

Since blogger doesn't support hierarchical, I guess I'll just muddle along for now.  If my number of tags gets unwieldy, I can look at maybe leveraging the alphabetizing model to represent the hierarchy.  For example:

rants
technical
technical-science
technical-software
technical-software-coding

I don't like that much, partly because the important part of the tag name becomes the last part, whereas the eye is drawn to the first part, obscuring the intent.  Also, what if I want rants to be last?  I guess I could do this instead:

01-technical
02---software
03-----coding
04---science
05-rants

That lets me order them any way I want to.  But wow, what a pain if I want to insert a new tag, like say, software design.  I'll have to renumber all the tags below it.  I guess I could do the old BASIC trick of numbering them by 10s...  (Who me?  Program in BASIC?  How old do you think I am, anyway?)

Another thought: assuming that each tag is simply a fixed URL, I could create a wiki page of the tag links and organize them any way I want to.  I could then simply have a pointer to that page on the blog.

Ah well, enough thinking about this.  Like I said, I'll just leave it a hodge-podge for now.

Content Publishing

I created a page where I am basically talking to myself about the various ways that content can be published on the Internet, and which way(s) I might want to concentrate on.  It is of minimal interest to anybody else.

http://www.geeky-boy.com/w/Sford_Content_Outlets.html

At present, I'm a minimal publisher, splitting content between my wiki and my blog.  New Wiki content is sometimes announced in the blog - like this very post.  (I also have a twitter and facebook accounts which I don't use due to low signal-to-noise ratios.)

LinkedIn Endorsements

LinkedIn Endorsements: you've probably received some.  Maybe you've given some.  I'm pretty much ignoring them.

I've been endorsed for software skills by people who have no software experience.  Friends and relatives endorse each other even though they have no first-hand experience with that person's skills.  It's like measuring a person's likability based on how many times they've been "liked" on FaceBook - it has more to do with the number of people you're connected to.  Popularity is not a measure of skill mastery.

The cynical part of me thinks LinkedIn created them as a mental virus for the sole purpose of getting people to sign in more often, so they can get their ads to more eyeballs.  (The cynical part of you might be saying, "Duh!")  Similar to chain letters, the system asks you to endorse your connections, which sends emails, which prompts those people to sign on and issue endorsements.

All that said, I don't want to be antisocial.  If you want me to endorse you for anything, let me know; I'll click as many skills as you like.  And thank you for the good thoughts behind your endorsements of me.

Just don't use LinkedIn endorsements to evaluate my technical skills.

FYI - I consider LinkedIn recommendations to be different.  Although they are susceptible to the same "you scratch my back, I'll scratch yours" reciprocity, I do consider them more useful then endorsements.  For one thing, there's a bit more accountability - your name is on your recommendation.  Also, they contain more information than a simple check mark.


UPDATE

Ok.  I surrender.  I went through my whole list of contacts and basically gave everybody a bunch of endorsements.  I still think they are of near-zero value, and I won't ever use them to evaluate somebody else's experience.

I guess they're kind of like valentines - sure, we all know that Valentine's day is a manufactured holiday, and is commercialized, and it's more "real" to show your love through non-scripted acts, and blah blah blah.  But you know what?  SUCK.  IT.  UP.  Give the damn Valentine card, along with a pot o' posies or a box o' chocs.  Its not rational, but since when are humans bastions of rationality?  It's just a form of social currency that you ignore at your own peril.

So yeah.  I've gone through my whole list and given lots of endorsements.  (And I got a flurry of them in return.)  One more form of social currency to contend with.

What's this Blog for?

I don't know. At this point, it's for playing around and experimenting. I don't have the time or energy to post often enough to support a general audience, so I don't see myself becoming a "blogger" any time soon. But I may contribute technical content to a corporate blog and might want to post occasional non-corporate stuff related to my corporate postings. This is pure speculation, of course; chances are that this blog will die a quiet death of neglect.

Update (21-Jan-2013): I guess this is becoming what many blogs are - a hodge-podge of whatever I feel compelled to write about at the time.

That raises a question - from the time of its creation (Aug-2007) till very recently, the blog was door-nail dead.  Did I not feel compelled to write during the past 12 years?  The answer is yes, I have felt the impulse to write stuff all along.  But I didn't have time to do anything so frivolous as blogging.  I still don't have time to blog, but at this point in my life I figure I can get away with making more time to do frivolous things.

UPDATE (12-Jun-2014): Wow!  2014 is not yet even half done, and I've already produced more posts than the previous 7 years combined!

I see from stats that my page views is going up, but is still trivial compared to "popular" blogs.  But that doesn't bother me much.  In fact, the only thing that bothers me a little is the thought that I'm giving a lecture to an auditorium full of empty seats -- that's rather embarrassing.  Fortunately, neither I nor anybody else has any way of proving that I'm talking to myself, and at my age embarrassment is the least of my worries.  I enjoy posting, and as pointless hobbies go, this one is sure cheap.  :-)