Tags: chat

Picture someone tediously going through a spreadsheet that someone else has filled in by hand and finding yet another error.

“I wish to God these calculations had been executed by steam!” they cry.

The year was 1821 and technically the spreadsheet was a book of logarithmic tables. The frustrated cry came from Charles Babbage, who channeled his frustration into a scheme to create the world’s first computer.

His difference engine didn’t work out. Neither did his analytical engine. He’d spend his later years taking his frustrations out on street musicians, which—as a former busker myself—earns him a hairy eyeball from me.

But we’ve all been there, right? Some tedious task that feels soul-destroying in its monotony. Surely this is exactly what machines should be doing?

I have a hunch that this is where machine learning and large language models might turn out to be most useful. Not in creating breathtaking works of creativity, but in menial tasks that nobody enjoys.

Someone was telling me earlier today about how they took a bunch of haphazard notes in a client meeting. When the meeting was done, they needed to organise those notes into a coherent summary. Boring! But ChatGPT handled it just fine.

I don’t think that use-case is going to appear on the cover of Wired magazine anytime soon but it might be a truer glimpse of the future than any of the breathless claims being eagerly bandied about in Silicon Valley.

You know the way we no longer remember phone numbers, because, well, why would we now that we have machines to remember them for us? I’d be quite happy if machines did that for the annoying little repetitive tasks that nobody enjoys.

I’ll give you an example based on my own experience.

Regular expressions are my kryptonite. I’m rubbish at them. Any time I have to figure one out, the knowledge seeps out of my brain before long. I think that’s because I kind of resent having to internalise that knowledge. It doesn’t feel like something a human should have to know. “I wish to God these regular expressions had been calculated by steam!”

Now I can get a chatbot with a large language model to write the regular expression for me. I still need to describe what I want, so I need to write the instructions clearly. But all the gobbledygook that I’m writing for a machine now gets written by a machine. That seems fair.

Mind you, I wouldn’t blindly trust the output. I’d take that regular expression and run it through a chatbot, maybe a different chatbot running on a different large language model. “Explain what this regular expression does,” would be my prompt. If my input into the first chatbot matches the output of the second, I’d have some confidence in using the regular expression.

A friend of mine told me about using a large language model to help write SQL statements. He described his database structure to the chatbot, and then described what he wanted to select.

Again, I wouldn’t use that output without checking it first. But again, I might use another chatbot to do that checking. “Explain what this SQL statement does.”

Playing chatbots off against each other like this is kinda how machine learning works under the hood: generative adverserial networks.

Of course, the task of having to validate the output of a chatbot by checking it with another chatbot could get quite tedious. “I wish to God these large language model outputs had been validated by steam!”

Sounds like a job for machines.

You know how when you’re on hold to any customer service line you hear a message that thanks you for calling and claims your call is important to them. The message always includes a disclaimer about calls possibly being recorded “for training purposes.”

Nobody expects that any training is ever actually going to happen—surely we would see some improvement if that kind of iterative feedback loop were actually in place. But we most certainly want to know that a call might be recorded. Recording a call without disclosure would be unethical and illegal.

Consider chatbots.

If you’re having a text-based (or maybe even voice-based) interaction with a customer service representative that doesn’t disclose its output is the result of large language models, that too would be unethical. But, at the present moment in time, it would be perfectly legal.

That needs to change.

I suspect the necessary legislation will pass in Europe first. We’ll see if the USA follows.

In a way, this goes back to my obsession with seamful design. With something as inherently varied as the output of large language models, it’s vital that people have some way of evaluating what they’re told. I believe we should be able to see as much of the plumbing as possible.

The bare minimum amount of transparency is revealing that a machine is in the loop.

This shouldn’t be a controversial take. But I guarantee we’ll see resistance from tech companies trying to sell their “AI” tools as seamless, indistinguishable drop-in replacements for human workers.

Back in 2014 Vitaly asked me if I’d be the host for Smashing Conference in Freiburg. I jumped at the chance. I thought it would be an easy gig. All of the advantages of speaking at a conference without the troublesome need to actually give a talk.

As it turned out, it was quite a bit of work:

It wasn’t just a matter of introducing each speaker—there was also a little chat with each speaker after their talk, so I had to make sure I was paying close attention to each and every talk, thinking of potential questions and conversation points. After two days of that, I was a bit knackered.

Last month, I hosted an other event, but this time it was online: UX Fest. Doing the post-talk interviews was definitely a little weirder online. It’s not quite the same as literally sitting down with someone. But the online nature of the event did provide one big advantage…

To minimise technical hitches on the day, and to ensure that the talks were properly captioned, all the speakers recorded their talks ahead of time. That meant I had an opportunity to get a sneak peek at the talks and prepare questions accordingly.

UX Fest had a day of talks every Thursday in June. There were four talks per Thursday. I started prepping on the Monday.

First of all, I just watched all the talks and let them wash me over. At this point, I’d often think “I’m not sure if I can come up with any questions for this one!” but I’d let the talks sit there in my subsconscious for a while. This was also a time to let connections between talks bubble up.

Then on the Tuesday and Wednesday, I went through the talks more methodically, pausing the video every time I thought of a possible question. After a few rounds of this, I inevitably ended up with plenty of questions, some better than others. So I then re-ordered them in descending levels of quality. That way if I didn’t get to the questions at the bottom of the list, it was no great loss.

In theory, I might not get to any of my questions. That’s because attendees could also ask questions on the day via a chat window. I prioritised those questions over my own. Because it’s not about me.

On some days there was a good mix of audience questions and my own pre-prepared questions. On other days it was mostly my own questions.

Either way, it was important that I didn’t treat the interview like a laundry list of questions to get through. It was meant to be a conversation. So the answer to one question might touch on something that I had made a note of further down the list, in which case I’d run with that. Or the conversation might go in a really interesting direction completely unrelated to the questions or indeed the talk.

Above all, these segments needed to be engaging and entertaining in a personable way, more like a chat show than a post-game press conference. So even though I had done lots of prep for interviewing each speaker, I didn’t want to show my homework. I wanted each interview to feel like a natural flow.

To quote the old saw, this kind of spontaneity takes years of practice.

There was an added complication when two speakers shared an interview slot for a joint Q&A. Not only did I have to think of questions for each speaker, I also had to think of questions that would work for both speakers. And I had to keep track of how much time each person was speaking so that the chat wasn’t dominated by one person more than the other. This was very much like moderating a panel, something that I enjoy very much.

In the end, all of the prep paid off. The conversations flowed smoothly and I was happy with some of the more thought-provoking questions that I had researched ahead of time. The speakers seemed happy too.

Y’know, there are not many things I’m really good at. I’m a mediocre developer, and an even worse designer. I’m okay at writing. But I’m really good at public speaking. And I think I’m pretty darn good at this hosting lark too.

I’ve been on a few different podcasts recently.

The tenth episode of the Design Systems podcast is myself and Chris having a back-and-forth about design systems: Overcoming Entropy and Turning Chaos Into Order:

Chris and Jeremy Keith discuss imbuing teams with a shared sense of ownership of their design system, creating design systems able to address unforeseen scenarios, design ops as an essential part of an effective design system, and more.

Gerry has started a new podcast to accompany his new book, World Wide Waste. He invited me on for the first episode: ‘We’ve ruined the Web. Here’s how we fix it.’:

Welcome to World Wide Waste, a podcast about how digital is killing the planet, and what to do about it. In this session, I’m chatting with Jeremy Keith. Jeremy is a philosopher of the internet. Every time I see him speak, I’m struck by his calming presence, his brilliant mind and his deep humanity.

We talked about performance, energy consumption, and digital preservation. We agreed on a lot, but there were also points where we fundamentally disagreed. Good stuff!

If you like the sound of some Irishmen chatting on a podcast, then as well as listening to me and Gerry getting into it, you might also enjoy the episode of The Blarney Pilgrims podcast that I was on:

Jeremy Keith is the founder and keeper of thesession.org, probably the greatest irish music resource in the world. And this episode hopefully has something of the generous essence of that archive. We flow, from The North as a different planet to Galway as the centre of the ’90s slacker world. From the one-tune-a-week origin of thesession.org and managing an online community to the richness and value of constancy.

I’ve already written about how much this meant to me.

On the same topic—Irish music on the web—I made a brief appearance in the latest episode of Shannon Heaton’s Irish Music Stories, Irish Tunes in the Key of C-19:

How are traditional musicians and dancers continuing creative careers and group music events during the Covid-19 pandemic? How is social distancing affecting the jigs and reels? In this unexpected open of Season Four of Irish Music Stories, musicians from Ireland, England, Belgium, Sweden, and the U.S. address on and offline strategies… from a safe distance.