Travel Advice from Bing Chat

Over the last three weeks, I've been playing with Bing Chat as a sort of international travel and language advisor, and I've learned a few interesting things along the way that may help others get more creative with how they use AI.

There are three main categories where I've found Bing Chat helpful:

  • Generating ideas of where to go and what to do next
  • Translating phrases that straddle nuanced cultural differences dictionaries and translation software can
  • Answering "why" questions that would normally require a human

There's also one "gotcha" that's particularly interesting, but I'll cover that at the end.

Turns out, there's more to it…

Go To Yakushima

Today I'd like to tell you about a very special place that not very many people will ever get the opportunity to visit.

After concluding my duties as a field reporter of RubyKaigi 2023, I found myself with a luxurious seven or eight days to myself. While at Kaigi, I asked several Japanese friends where I should visit in the southern island of Kyushu. Almost to a person, they said "Kagoshima".

So, I went. And it was great! The weather was warm, the nature was beautiful, and the people were easygoing.

Immediately, I wanted to go deeper. I got it in my head that if I went somewhere even more inaka I could prove I was a Real Vlogger by going on an adventure and then making a YouTube Short set to an epic piano score.

But… where to?

And before you knew it…

Apple’s LiveText is incredible

I mean, just look at this screenshot. I can confidently take a photo of a friend’s hand-written note, search for one Japanese word that I knew was written on it to find it, then select the text and paste it into a translation app, maps, etc.

Coin lockers

In Japan, it's customary to use a coin locker at a train station to store your bags, so that you can spend time visiting a place without lugging all your stuff everywhere.

Unfortunately, this coin locker only takes five ¥100 coins (I've been spoiled by newer ones in Tokyo and Osaka that take IC cards like Suica) and I only had a single ¥100 coin on me.

So I went to a 7-Eleven to change a ¥1000 bill to coins and the attendant told me that they can no longer break change. So then I bought a bottle of tea in cash, but because these days you pay with cash using an automatic machine mounted in front of the register, it gave me back one ¥500 coin and three ¥100 coins. So I still only had four ¥100 coins when I needed five to use the locker.

So then I turned around and bought a donut with the ¥500 coin in order to break change again and this time I received three more ¥100 coins.

All so that I could pay ¥500 to use a coin locker… always an adventure!

A convenient truth

Lots of good convenience store discoveries this week!

  • A pizza sandwich filled with wieners and taco meat.
  • Bread-flavored gummies.
  • Fried and seasoned chicken skin, closely resembling the bottom of a KFC bucket
  • A canned whiskey that comes pre-mixed with water.
  • Individually-packaged cups of orange jelly housed in a larger cup
  • Sparkling water that's been fortified with… a lot of fiber?
  • Tangerine-flavored gummies designed to look like little popsicles
  • Frozen chocolate banana chunks made with otherwise-wasted bananas

So much innovation!

Kanazawa's all right

Had a great half day in Kanazawa, even though it wound up being a bit of a speed run. Omicho fish market and Kenrokuen garden are both popular tourist spots, but I found the local restaurants and bars to be really exceptional, both in service and food quality. If you like fresh fish, you really must visit someday!

Golden Week Rush

I'll never understand cultures that synchronize everyone's vacation time. Similar to August throughout Europe, most Japanese folks get Golden Week off in May. The upshot is that everywhere is crowded, hotels are expensive, and there's nothing to do because everything's closed.

The first 5 restaurants I'd picked out in Shinbashi were all closed. Presumably, because their Tabelog rankings were high enough to justify the lost revenue. Alas.

I'm staying at a hotel with an (onsen-style) public bath and so I wore the provided yukata and slippers to the bath. But when I got out, someone had taken my slippers.

So then I had to decide if I was going to be the gaijin that steals some other person's slippers or the gaijin that walks through the hotel lobby barefoot like some kind of animal.

No good option.

I had too much to drink last night so I immediately checked my phone upon waking to make sure I stayed out of trouble and realized that all I did was write a (5-star!) review on ProductHunt for buttondown.email

What the hell's wrong with me.

Ten Trips

Since my study abroad in 2005, this marks the tenth time I've visited Japan. It's amazing how much technology has changed the experience of international travel. The convenience is undeniable, but it feels like I'd be lying if I said I didn't miss the challenge of having to figure out how to survive with no Internet access.

Heading to Japan this morning to undertake my first field report as a Test Double foreign correspondent.

My Uber arrived early, we encountered no traffic, and I breezed through security. Even the Delta lounge was empty. So with my luck, that means my flight is sure to disappear over the Pacific.

Nice knowing you!

Blue Sky, Red Ocean

I became familiar with Blue Ocean Strategy in the context of Nintendo's decision to forego the "console wars".

Instead of pushing to design consoles with the fastest chips and best graphics, they embarked on quirky industrial designs and user experiences with seeming tangents like the Nintendo DS, the Wii, the 3DS, the Wii U, and the Switch. The big idea (as it was baby-birded to me via amateur videogame journalism) was that competing with Sony and Microsoft to have the highest-performance machine or the best-looking version of multi-platform games was a losing proposition. It represented competing in a so-called "red ocean" (as in, there's blood in the water). Why? Because there were already two well-funded competitors vying to sell the exact same thing. The best Nintendo could hope to do was be marginally better, despite being in a far weaker capital position, with less access to the top chipmakers, and with a stable of IP that didn't necessarily benefit as directly from better graphics. So they pursued a blue ocean strategy by creating bold (and occassionally bizarre) products that couldn't be compared apples-to-apples with the competition.

The rapid, unscheduled disassembly of Twitter-dot-com over the last six months has resulted in an ocean of opportunity emerging. Tons of entrants are getting in. Mastodon was already there. Hive was there for a couple weeks, too. Journalists toyed with giving up the one thing they really care about—drip-feed dopamine from constant notifications—to join Post.news. Meta is apparently building a Twitter-like platform with ActivityPub support. Spoutible is a thing, I guess. And this week, everyone's talking about Bluesky, the open and federated but nevertheless locked-down and invite-only Twitter clone that started under Jack Dorsey Twitter and whose new app looks more like Twitter than Twitter does.

All these real-time, text-based activity streams are pouring chum straight into a deep red ocean.

Turns out, there's more to it…

Fun fact: this Apple Support document is just flat-out wrong. It says: "you can identify [a fast charging] cable from other chargers by the USB-C connector and the aluminum around the magnetic charger", but the very short 0.3m USB-C cable Apple started selling in 2018 and has since discontinued meets these criteria and, wouldn't you know it—can't fast charge an Apple Watch.

As someone who travels light, I figured I'd bring my 0.3m cable if I could. Because the Internet provided zero help here, I figured I'd feed the web to mention that as of 2023, the only Apple Watch chargers that support fast charging are 1 meter long. Oh well.

Maybe it's because this came out of a reputable institution like Stanford, but this project feels wildly irresponsible. Not only because OpenAI's language models frequently hallucinate complete nonsense, but because the app uploads your entire aggregate health data to OpenAI.

Apple went to pretty absurd lengths to keep individuals' health data private and secure. While various apps that integrate with Apple Health access more data than they need and surely phone home too much of it back to their application servers, the idea of just blasting all your health data carte blanche at OpenAI seems… bad, maybe?

This disclaimer doesn't inspire much confidence:

HealthGPT is provided for general informational purposes only and is not intended as a substitute for professional medical advice, diagnosis, or treatment. Large language models, such as those provided by OpenAI, are known to hallucinate and at times return false information. The use of HealthGPT is at your own risk. Always consult a qualified healthcare provider for personalized advice regarding your health and well-being. Aggregated HealthKit data for the past 14 days will be uploaded to OpenAI. Please refer to the OpenAI privacy policy for more information.

Hopefully the fact that you have to jump through a bunch of hoops to build and install this thing means few people will use it and nobody will end up hurting themselves, but if it was in the app store it's hard to imagine this not leading to a lot of really bad health outcomes. (And that's the best case scenario—imagine if OpenAI one day changes their privacy policy and starts selling a version of the language model to insurance underwriters that's tuned with user-submitted stuff like this.)

It's been a while since I've had an excuse to read a Detroit Free Press article, but this story warmed my heart a bit given that it's a certainty everyone who works at GM corporate will have seen it.

Car makes are simultaneously:

  1. Terrified of becoming a commodity, since electric motors and batteries are much harder to differentiate than traditional ICE drivetrains

  2. Aroused by the idea of becoming a software platform that can capture 30% of revenue as you sit around with nothing better to do than watch ads and play Candy Crush in your increasingly-autonomous vehicle

Normally, I'd be worried that this would lead to a domino effect over the next decade that effectively locks CarPlay out of all new car models, but Apple's brand power makes that unlikely. As soon as a few major manufacturers ditch Apple, enough competitors will smell blood and seize the opportunity to differentiate themselves by riding Apple's ecosystem coattails. Even if it comes at the cost of post-sale recurring revenue.

Also good to see Ford PR takes the easy layup. As a lifelong Ford customer, the only thing that'd make me ditch them now is if they dropped support for Apple stuff (in general their CarPlay implementations have been industry-leading):

We continue to offer Apple Carplay and Android Auto because customers love the capability that enables easy access and control of their smartphone apps, especially our EV customers.

I asked Bing Chat to: "Write a blog post in the style of Justin Searls about why React was a mistake."

In its response, which I threw up in a gist, it was better than I expected.

This, indeed, sounds pretty close to something I'd type in a first draft:

Secondly, components are not a good fit for humans. Humans are not good at managing complexity, especially when it comes to code. Components add complexity by creating more moving parts, more dependencies, and more sources of truth. Components also add complexity by creating more cognitive load, more mental models, and more context switches.

By asking AI to write something in my own style, I can spot the tool's weaknesses is a little better. Normally we say something is "rough around the edges", but in the case of LLMs, the edges are the only part they typically nail. It's the warm gooey center of each sentence that needs work.

I was telling my friend Ken last night that GPT-4 produces "incredibly sentencey sentences", which is great. It's one of the things I most want from a sentence. But it can lull us into thinking the sentences really say anything. There just isn't much meat on the bone. It's all hand-wavey filler for the most part.

That said, this sounds like exactly something I'd write:

Embrace the web as it is. Don’t try to reinvent the wheel with components. Use HTML elements as your building blocks. Use CSS rules as your styling system. Use JavaScript functions as your logic units.

From the excellent GQ profile posted a couple weeks ago:

“We try to get people tools in order to help them put the phone down,” Cook says, gently. “Because my philosophy is, if you’re looking at the phone more than you’re looking in somebody’s eyes, you’re doing the wrong thing. So we do things like Screen Time. I don’t know about you, but I pretty religiously look at my report.”

I have a young child who is, perhaps predictably, obsessed with my phone—he chases it around the room. When I share this with Cook, he nods with something between recognition and reproach. “Kids are born digital, they’re digital kids now,” Cook says. “And it is, I think, really important to set some hard rails around it. We make technology to empower people to be able to do things they couldn’t do, to create things they couldn’t create, to learn things they couldn’t learn. And I mean, that’s really what drives us. We don’t want people using our phones too much. We’re not incentivized for that. We don’t want that. We provide tools so people don’t do that.”

It's hard to take Cook seriously about this in the context of a two sentence statement in a keynote video, but this reads as believable.

I still think about my first dinner out after buying the original iPhone in 2007. Becky and I went to P.F. Chang's and I sat there helplessly trying to load articles over AT&T's garbage Edge network, ignoring my (phoneless) spouse. She made her dissatisfaction known, and we've been pretty firm about not using phones around each other ever since.

The fact that it was "smart" wasn't what made the iPhone so addictive, it's that it was also nice to use. And that combo is why it has become so dangerous when used thoughtlessly.

I'm grateful for those early experiences where I was the only one with a (recognizable) smartphone in a space. Once, walking down an airplane aisle, I remember being stopped by four or five passengers if "that" was an iPhone. Because other people saw me glued to my phone and judged me for how unnatural that seemed, I had it baked in my head the truth that it is unnatural and needs to be handled with the same level of care as any foreign object that human evolution couldn't have prepared us for.

Apple's tools around Screen Time, Focus modes, notifications, etc., are a confusing mess. That they exist at all is, I suppose, a blessing owed to Cook's stated beliefs above. But for Apple to escape culpability in fostering information addiction in half the world's population, they need to do more than provide a hodge podge of arcane configuration options. They need to make it as easy to be empowered without distraction as they strive to make other experiences feel seamless. It feels really natural to pair some AirPods to an iPhone. It should feel that straightforward to configure settings that better establish that the phone works for the user, as opposed to the other way around.

This is actually one way in which the dystopian film Her gives me a bit of hope. If an on-device AI built with a large language model can be made to act as a personal assistant, it could run interference on the users behalf, dismissing some notifications, acting on others, and reminding users when their on-device activities are at odds with their stated goals or even a healthy mental state.

Putting AI to work on behalf of the user is a surprisingly achievable thing, and Apple is well-positioned to do it in a way they were never in a position to compete with the surveillance capitalism of ad-based social networks. This is as much the next frontier as AR/VR is, and it's worth more attention than I suspect it's getting.

My cousin just contacted me for the first time in a decade to ask for advice on planning her first trip to Japan. As if to punish her, I turned around 3000 words in under two hours. That'll teach her!

(Maybe I can salvage a blog post from it, at least…)

I was getting free Paramount+ through my T-Mobile account, but that promotion ended, so now I get it through my American Express Platinum card, which offers a free Walmart+ subscription (via statement credits), which in turn includes a free Paramount+ subscription. walmart.com/partner/plus/amexplatinum

Ok good talk.

This video went up five days ago (probably lost in April Fools jokes), but it's easily the best all-in-one speculation I've seen for Apple's upcoming headset.

Two thoughts:

  1. As someone who's owned six VR headsets, Apple is absolutely right to be focused on weight above almost any considerations. Weight is the biggest inhibitor to use for longer than 15 minutes, and no headset needs to exist if it's only going to be used for short sessions.
  2. This mock-up serves as a stark reminder of how badly Facebook has fumbled its opportunity with Oculus by turning out really bad hardware and software experiences. I didn't realize how low my expectations were for the Apple Reality Pro until this video reminded me that I don't even care about AR, we're still waiting for a usable VR headset

Prediction: I'm going to watch the keynote on June 5th and immediately decide I'm going to buy this