Jeremy Keith

Boom! The Clearleft podcast is back!

The first episode of season four just dropped. It’s all about design transformation.

I’ve got to be honest, this episode is a little inside baseball. It’s a bit navel-gazey and soul-searching as I pick apart the messaging emblazoned on the Clearleft website:

The design transformation consultancy.

Whereas most of the previous episodes of the podcast would be of interest to our peers—fellow designers—this one feels like it might of more interest to potential clients. But I hope it’s not too sales-y.

You’ll hear from Danish designer Maja Raunbak, and American in Amsterdam Nick Thiel as well as Clearleft’s own Chris Pearce. And I’ve sampled a talk from the Leading Design archives by Stuart Frisby.

The episode clocks in at a brisk eighteen and a half minutes. Have a listen.

While you’re at it, take this opportunity to subscribe to the Clearleft podcast on Overcast, Spotify, Apple, Google or by using a good ol’-fashioned RSS feed. That way the next episodes in the season will magically appear in your podcatching software of choice.

But I’m not making any promises about when that will be. Previously, I released new episodes in a season on a weekly basis. This time I’m going to release each episode whenever it’s ready. That might mean there’ll be a week or two between episodes. Or there might be a month or so between episodes.

I realise that this unpredictable release cycle is the exact opposite of what you’re supposed to do, but it’s actually the most sensible way for me to make sure the podcast actually gets out. I was getting a bit overwhelmed with the prospect of having six episodes ready to launch over a six week period. What with curating UX London and other activities, it would’ve been too much for me to do.

So rather than delay this season any longer, I’m going to drop each episode whenever it’s done. Chaos! Anarchy! Dogs and cats living together!

I’d like to play it cool when I announce the latest speakers for UX London 2023, like I could be all nonchalant and say, “oh yeah, did I not mention these people are also speaking…?”

But I wouldn’t be able to keep up that façade for longer than a second. The truth is I am excited to the point of skittish gigglyness about this line-up.

Look, I’ll let you explore these speakers for yourself while I try to remain calm and simply enumerate the latest additions…

• Ignacia Orellana, Service design and research consultant,
• Stefanie Posavec, Designer, artist and author, and
• David Dylan Thomas, Author, speaker, filmmaker.

The line-up is almost complete now! Just one more speaker to announce.

I highly recommend you get your UX London ticket if you haven’t already. You won’t want to miss this!

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.