digging in to ChatGPT and similar AI stuff

I’ve successfully been ignoring all the hype around ChatGPT and similar AI stuff all through this year.

I was initially amused by some of the stuff folks were posting to Twitter when ChatGPT and DALL-E and other tools were made publicly available. There was a lot of funny stuff out there, with folks getting oddball results out of the chatbots, and using the image generators to make some really crazy images. Initially, it seemed pretty harmless, but also fairly useless.

Then came the op-eds and think pieces from people worried about the impact that these things could have on the world. Everything from worry about AI causing human extinction, to ChatGPT replacing writers and programmers, to the environmental cost of running all this stuff. A lot of that was overblown, I think.

But recently, something pushed me over the edge and I decided I had to start learning some of this stuff. I’m not even sure what did it, exactly. Either way, I’ve been digging into this stuff, and I thought I’d write up some notes.

First, I’ve been looking at two primary categories of “AI” here: the LLM chatbots, and the image generators. I like playing around with the image generators, but I haven’t found much practical use for them, and they’re not that interesting to me, so I’m going to skip talking about those. I’ll just say that the Bing image creator is pretty fun to play with.

As to the LLM chatbots, I’ve started playing around with ChatGPT and a few others. I registered for a free account with ChatGPT, which gets me access to GPT-3.5.  Upgrading to ChatGPT Plus for $20/month would get me access to GPT-4, which is supposed to be much better. I don’t think I’ll be doing that, but a number of people seem to think it’s worth it.

At work, we have our own chatbot called “Mindspark”, which is powered by Azure OpenAI, which in turn uses GPT-4 and/or GPT-3.5, if I’m understanding it correctly. It’s internal-facing, and at this point, really just an experiment, I think. I’m not sure if there are any long-term plans for it. Anyway, it’s reasonably good, and also one of the only options, from my work computer. For some reason, we block access to ChatGPT’s web interface, so I can’t use that directly at work. (Which is one of the reasons why I probably wouldn’t pay $20/month for ChatGPT Plus. If I was paying for it, I’d want to have access to it at work and not just at home.) I’ve also noticed that we block Perplexity, and I expect some of the other popular tools. (I’m not sure why, though I’d guess it has something to do with distrust of the privacy policies for those tools and worry that proprietary corporate info will get into them and then maybe leak back out?)

I’ve also played around with Poe, which is a tool that gives you access to a bunch of different AI tools, including ChatGPT. They also have a $20/month plan that gets you access to more advanced models, and lets you use it more. I’m not sure how worthwhile that is, vs. using ChatGPT directly. I guess there’s some utility in having access to multiple sources through a single interface. I definitely want to play around with it some more.

And I’ve tried out the new Bing chat. It’s also powered by GPT under the hood, I think. The nice thing about Bing chat is that, unlike the free version of ChatGPT, it combines web search with GPT, so that it can return more recent information than using ChatGPT alone. (And my company doesn’t block Bing chat, so I can use it at work.)

So that’s my brief overview of the front-end interfaces for LLM back-ends that I’ve tried out. I haven’t found one that is noticeably better than the others, at this point, but I haven’t done much with them yet.

I should also mention that all of these things, for a lot of the use cases I’ve tried, are spectacularly bad at returning correct and/or useful data. In general, I’m not sure if they’re super useful as general research assistants. If you can find an answer to a question with a regular web search or a simple Wikipedia check, that’s way better than asking ChatGPT.

Aside from just playing around with these things, I’ve also been reading some articles and listening to some podcasts. I thought I’d include some podcast links here, for reference.

  • Here’s an episode of the New Yorker Radio Hour from a few months ago, where they did an interview with Sam Altman, CEO of OpenAI. It’s somewhat interesting, at a high level.
  • Ezra Klein has done a few shows talking about AI and LLMs and stuff. Some of it is pretty interesting to me, but it’s mostly high-level philosophical stuff, and I’m not sure what I think about some of it.
  • On the more practical side, Scott Hanselman did an episode of his podcast recently where he interviewed a guy who wrote a book on “prompt engineering”. That’s the kind of thing that made me roll my eyes, until I started digging into it a bit. I still think the whole prompt engineering thing is a bit overblown, and I don’t want to read a whole book about it, but I’ll admit that some of it is useful, and I have now watched a couple of LinkedIn Learning videos on the subject.
  • Also on the practical side of things, I’ve queued up a few episodes of .NET Rocks related to AI. This one, from August, looks interesting.
  • And there’s a recent episode of RunAs Radio that got into some good no-nonsense explanations for how LLMs work. I think that episode has a better explanation of the tech involved than anything else I’ve read or listened to. (I’m sure there are other good explanations out there, of course, but this is the best one I’ve stumbled across so far.)
  • And, finally, related to .NET Rocks, I see that Carl has a video series called The AI Bot Show that covers this stuff. I guess I’m going to have to watch some of those.

So, in conclusion, I guess I’m doing a little less eye-rolling at this stuff now. I see some utility in it, and I’m getting a better idea of what it’s good for and what it’s not good for.

 

LoTR, and Neil Gaiman, and life in 2001

I’m currently reading Neil Gaiman’s Adventures in the Dream Trade, which is a collection of miscellaneous stuff, including introductions he’s written for other people’s books, some poetry and song lyrics, and a bunch of his blog entries from 2001, right after he had finished writing American Gods and was beginning the process of promoting it. I’m in that section now, and have made it through to mid-2001, when he had wrapped up his US book tour and just started his UK tour. I’m wondering how far into 2001 this goes, and whether or not we get as far as September 11, and what his thoughts might be on that.

I’ve also been rewatching the Lord of the Rings movies, including listening to some of the commentaries, and also listening to the Ringheads podcast, which has been discussing the movies at length (about 10 hour-long episodes per movie). The Fellowship of the Ring was released in 2001, with Two Towers coming out in 2002 and Return of the King in 2003. I’d gone into NYC to see a presentation on the first movie in September 2001, just a couple of days before 9/11.

So reading Gaiman’s blog entries, and watching the LOTR movies, has got me living in the past a bit this weekend, for better or worse. Gaiman’s blog was, at the time, done with Blogger, which I was also using at that time. (I started this blog in June 2001.) So reading about his struggles with Blogger brings back some memories. And he writes about buying a Japanese laptop from Dynamism, which is a company that used to import nifty laptops from Japan. (I’d never bought anything from them, but I know at least one person who did, and I was a bit jealous of his nifty Japanese laptop.) And there are mentions of early e-readers, and other fun esoteric stuff.

There are links in many of those blog entries, some of which still work and some of which don’t. It’s been interesting to follow some of them, and get sucked back into the web circa 2001. The review of American Gods from sfsite.com is still up, but the site itself seems to be pretty much dead, having gone on hiatus in 2018. SciFi’s Seeing Ear Theatre is long gone, but there’s a good list of the stuff they did here, with some of it still available for download from various places. (I could go on with more of this, but you get the idea.)

This has all got me thinking about big events, and how we see things differently before and after them, and how there are weird unintended resonances in fiction sometimes. (I have more to say about that, but I’m struggling to get it into words properly, so I’m just going to leave it at that for now.) So, some good memories, and some mixed feelings, and some amusement at old forgotten tech.

 

Thanksgiving Eve

I had some PTO days to use up this year, so I decided to take this entire week off. Originally, I had some semi-ambitious half-formed plans about maybe going in to NYC and visiting some museums again, and maybe even staying overnight. But I got a bit sick a couple of weeks ago, and, while I’m mostly over that, I’m still not keen to go out in the cold, get on a train, and deal with NYC, crowds, and so on. So I’ve largely been sitting in my armchair reading comics, or sitting on the couch watching TV.

My Thanksgiving plans are, shall we say, minimal. I have no plans to go out, and I haven’t bought any traditional Thanksgiving foods. So maybe I’ll have a turkey and cheese sandwich for lunch, and a frozen turkey burger for dinner, and that’s about as close to honoring Thanksgiving as I’ll get.

Looking at some posts from previous Thanksgivings, I guess things could be worse. 2018 was a particularly bad year, with the snowstorm and the Christmas music debacle. Somerville hasn’t played Christmas music on Main St. in a few years, and hopefully they won’t start it up again this year. But there was one thing this year, from last weekend: some kind of issue with the sanitary line out of my apartment building that caused the building to have a bit of a stink going for a few days. (That actually almost moved me to go into NYC for a day or two, but they got it fixed before things got too bad.)

And for anyone who’s still reading after all that, here are some notes on the comics I’m reading this week, and the TV I’m watching.

I’ve read through a couple of B.P.R.D.: Hell on Earth omnibus volumes. I have all five, in hardcover. I bought them as they were coming out, in 2018 and 2019. I’d read most of the previous BPRD run in single issues. The end of that run and the start of Hell on Earth happened right when I’d stopped buying monthly books. So picking up the hardcovers for Hell on Earth seemed like a good idea. I don’t know if it really was though. Dark Horse has a 50% off sale going on right now for digital stuff, so if I’d waited and just bought the digital versions, I could have gotten all five for just over $30, and I wouldn’t have to worry about what to do with these big hardcovers once I’m done reading them.

And I did wind up spending some money on Hellboy-related stuff from that sale yesterday, including all of the Lobster Johnson volumes, and all of the Witchfinder volumes that I didn’t already have.

I’m mostly enjoying Hell on Earth, even though I’m not generally a big fan of post-apocalypse fiction. I should probably take a break from it, and read something different today, but I think I’m just going to go ahead and jump into the next volume. If I’m not enjoying it, then I’ll switch to something different.

For my TV watching, I finished season two of Locke & Key on Netflix. It’s a pretty good show. I’ve been listening to the Locke & Key: Unlocked podcast after watching each episode and that’s been fun. I’ve mentioned this before, but I do really like the idea of companion podcasts for TV shows. They can sometimes be too silly, or too fawning, but if you get the right mix of elements, they can be really good.

I’ve now started watching season four of The Expanse on Amazon. Season six is coming out soon, and I actually didn’t realize that I hadn’t even watched season four yet. I knew I hadn’t watched season five, but I thought I was only one season behind, not two. Either way, it’s been a good season so far. And on the podcast front, I’ve started downloading some season four episodes of The Churn podcast, which was originally the official SyFy channel podcast for The Expanse, back when it was on SyFy. Even though the show has moved to Amazon, I guess the podcast is still being done by SyFy, though I’m not completely sure about that. I’m also curious about the Ty & That Guy podcast, which is hosted by Ty Franck and Wes Chatham. That’s more of a rewatch podcast, I guess. They’ve only just gotten through season three. If they start season four soon, that might work out well for me.

I’ve been keeping current with Doctor Who: Flux, watching the episodes as they’re released. I’m getting them through Apple, so I can’t watch them until the day after they’re released, but that’s good enough for me. I have mixed feelings about this season, but hey… it’s Doctor Who! I haven’t had much luck in finding a good Doctor Who podcast. There are a lot of them! I did find one I liked a while back, but it seemed to be dead the last time I checked. Maybe I’ll try the Radio Times one.

And I will likely watch the first episode of the new Hawkeye series on Disney+ today. It seems to be loosely based on Matt Fraction’s Hawkeye run, which is very good. I read the first two volumes of it some time ago, and just bought volumes 3 and 4 from Comixology, where they’re currently on sale for $1.99 each.

I’ve found that my stay-at-home vacation routine is basically to read comics until my eyes are too tired for that, then watch TV until my eyes are too tired for that, then listen to podcasts until it’s time for bed. I can’t say that I’m proud of that, but it is what it is, and it’s about all I feel up to doing right now.

So I guess that’s about it for this low-stakes blog post. Honestly, I was mostly writing this because it’s too cold out to go for a walk and I don’t feel like doing any indoor exercise right now, and I’m not really ready to dig into any reading material just yet. I’m still waking up.