Yesterday, a group of MIT researchers released an article titled “Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights”. The piece describes a set of experiments which convincingly show OpenAI’s latest Astra model is able to understand and successfully alter raw weight data. Wowzers! It’s a rough analogy, but an LLM’s weights are sort of like its brain. A set of weights is a large pile of numbers generated during training, and an LLM’s output is derived by running input through the weights using some matrix multiplication and a bit of randomization. While the steps to generate weights are well understood, the weights themselves are extremely opaque. There’s ongoing work to try and explain how weights work, but researchers currently have a limited understanding of what these numbers do. Based on this, I was quite surprised to learn that LLMs are able to act on raw weight data — even if it’s still just in limited cases. It’s unclear if OpenAI’s model was trained on weight data. Even if it was, I still find these results surprising. The article shows the model accurately predicting what a never-before-seen set of weights was built to do, fixing another model by updating its weights, and creating new sets of weights that performed simple tasks. I would not have guessed any of that would be possible a couple of days ago. This whole thing is slightly unnerving. The whole “weights as a black box” thing has always felt a bit sketchy to me, even when I was working with much simpler machine learning models. Now these experiments hint at a future where LLMs could be self-improving in ways that aren’t human-verifiable. Machines building machines, and we can only hope that they’re not doing anything weird. I don’t know if this strategy is scalable, but I’d guess that it’s something more people will be exploring very soon. More and more often these days, I wish we were living in less interesting times.

After living with Apple’s 27.0 OSs since launch, I have some more annoyances to get off my chest. This time, it’s all about how tabs and menus have gotten worse. I’ve already ranted about the Liquid Glass material in general, but these two design changes in particular have really been grinding my gears. I’ll reiterate that Apple’s latest OSs look substantially nicer to me than the previous set… but that only makes these setbacks more glaring. Also, many of these issues aren’t nearly as bad in light mode — but I use dark mode exclusively on all platforms. Apple offers this appearance setting, so I think it’s fair to criticize them when it’s not holding up. First up, let’s talk tab bars. I think these looked awful in the original Liquid Glass redesign, and in 27.0 they look even worse. Below is an example of three tab bars from Safari in macOS. All of them are in dark mode. The top example is from macOS 26 with the “clear” Liquid Glass setting, the middle is macOS 27 with the default (mid-slider) version of Liquid Glass, and the bottom is macOS 27 with Liquid Glass at its most tinted. In each, the middle tab is selected (though I think the word “tab” is being quite generous to these globs). In macOS 26, there was practically no difference between the clear and tinted versions of tabs. Similarly, the clearest and default/middle tabs in macOS 27 are effectively the same. Because of this, I’m leaving out the redundant examples. Even though I still think it’s ugly, I vastly prefer the macOS 26 version of these three options. It offers the most contrast, and it makes more sense in dark mode: the background is darker and the foreground of the active tab is lighter. The middle example is what tabs look like in the default (mid-slider) version of Liquid Glass in macOS 27. There’s now only a very faint outline around the active tab, and practically no difference in background colours. To me, this is unreasonably subtle. The effect is even worse when there are a lot of tabs open. Lastly, there’s macOS 27 with the fully tinted Liquid Glass setting. It’s better, but it still looks less correct to me than the tab design from macOS 26. It’s difficult to put into words how much I loathe the look of this new tab bar design. I don’t mind the more “bubbly” look of Liquid Glass throughout the 27 OSs for the most part. It gives UI elements more dimension than in the 26 OSs. But it doesn’t work for tabs. Because the bubbly look is inside a trough, the active tab’s glass effect ends up looking like a blur on the top and bottom. This reduces contrast further and makes the active tab harder for me to pick out. Even in dark mode with full tint, I find the active tab less visually clear than in 26’s clear mode. Now, I’m sure there are at least a few people reading who don’t see what the fuss is about. If that’s you, I assure you that the difference is more stark when you’re not comparing things side by side. It’s not impossible for me to pick out the active tab, but I think it’s trickier than it needs to be! But, if you still don’t believe me, here’s a little experiment. Which of these do you think is most legible? The text/background colours in the above image are based on the foreground/background colours used in the tab bar instances above. First is clear in macOS 26, then the default from macOS 27, then fully tinted in macOS 27. I think they’re all pretty awful, but I prefer the macOS 26 clear version. Again, this is because I’m using dark mode. In dark mode, light text appears on a darker background. Similarly, active UI elements have a lighter background than their surrounding elements. I’m sure there are counter-examples, but this is how just about everything else works in Apple’s own apps! It should be noted that Safari uses the system default tab bar design. I also see this design in Apple’s Terminal app, in Pixelmator Pro, and elsewhere. I don’t use Xcode daily anymore, but you’ll also find them there — though in true Xcode fashion, they’re ever so slightly nonstandard and also don’t respect your tint setting. Below is a screenshot of Xcode using my current settings of dark mode with fully tinted Liquid Glass. Up next: menus. Below is an image showing four versions of the same menu in macOS. Top left is macOS 26 clear, top right is macOS 26 tinted, bottom left is macOS 27 default (mid-slider), and bottom right is macOS 27 fully tinted. It’s a similar story here. In macOS 26’s dark mode, I had no problem with system menus even when Liquid Glass was set to clear. In macOS 27, even in the fully tinted mode, the menus have much lower contrast. They also now lose all of Liquid Glass’s refractive effects when at their most tinted. I think this is less of an issue than the tab design changes, but it’s still a downgrade. Again, I’m certain many people don’t care about this. Some might wonder why I’m not turning on accessibility settings to help with these things, if they bother me so much. I’ve flirted with this (especially the “Increase Contrast” setting), but those settings have many knock-on effects. 1 But honestly, I don’t think accessibility settings should be required to have a reasonable amount of contrast in a design system. Maybe Apple disagrees, but I really hope more dark mode tweaks are coming. The “Increase Contrast” setting is under System Settings -> Accessibility -> Display -> Increase Contrast. Interestingly, you can use this setting along with the clearest version of Liquid Glass to almost get back to how things looked in macOS 26’s version of tinted. However, it adds contrast-y lines around many UI elements that I find extremely distracting. It also alters colours on some elements to, strangely, make them less contrast-y. It feels unevenly applied and poorly implemented in several apps. ↩

I really enjoy John Gruber’s podcast The Talk Show. However, I’ve noticed that it’s been a while since it was in my feed. I decided to chart previous episode dates to check some of my assumptions about release frequency. Cutting to the chase, here’s a link to The Talk Show Timeline. You can click/tap on days to get a pinned tooltip, which lets you link out to a particular day’s episode. I’ve tried to make this work well on mobile devices, but you’ll likely find it works best on desktop. A note about this: Gruber has mentioned in the past that there has been a personal situation that he’s been working through. He’s also mentioned something to this effect on the podcast at points, but hasn’t gone into detail. I don’t need to know more than has been said, and I just hope things are alright. I’ve read Gruber’s site since 2002 1 and listened to his podcasts since 2007. In that time, I’ve learned that he operates on his own timeline… and has a penchant for procrastination. No shade here! He’s set himself up with a work situation that I envy. I also don’t want to seem grumpy about the lack of podcast episodes; I’m just trying to understand how this current break compares to those in the past. Because it was easiest, and because it would answer my immediate questions, I only looked at the current iteration of The Talk Show. Happily, there’s a single page which lists all the episodes. It had a tiny bit of data weirdness, 2 but I was able to turn this into a JSON file with the details I cared about. With that, I used the calendar heatmap chart in Apache ECharts to display the episodes over time. Some things I noticed: While it’s been a while (29 days) since the last episode (on August 10), this isn’t unheard of. The average is about 12 days between episodes, but there have been 6 other times when the episode gap has been at least this long. The longest gap was 62 days between December 24, 2024 and February 24, 2025. There’s exactly one day with two episodes: July 19, 2014. It was “Cat Pictures” with Marco Arment, which got split into two “sides”. Here’s a link to side 1, and here’s side 2. I mentioned procrastination: 73% of episodes take place on the 16th of a month or later. 28% of episodes take place on either the last or second-last day of the month. Again, no shade! It’s something I chuckle about whenever I notice it. At the current rate, this year is about in line with output going back to 2023. While it has been a while since a new episode dropped, it’s not out of whack statistically. Anyway, this was a Labour Day project that was mostly for my own amusement. I expect there will likely be a new episode of The Talk Show some time fairly soon after tomorrow’s Apple event. I also don’t know if I’ll keep this chart up to date… though it’s not terribly onerous to do now, so who knows. I found Daring Fireball because I was researching the purchase of my first Mac around this time. It wasn’t until October of 2002, but I ended up buying one of the machines he wrote about in his first post that August. ↩ The following dates don’t match the main format: Sunday 30 November, 2025 Mon, 24 Feb 2020 16:05:34 EDT Tuesday 31 December 2019 Tuesday, June 25 2019 Sat, 16 Mar 2019 19:43:49 EDT Wednesday 31 December 2014 Monday, 30 Jun 2014 ↩

I mostly use my web stats service because I get a lizard-brain kick from watching numbers go up, but it also provides some fun insights. For example, it’s how I found out about bubbles.town. At first I thought this might be a Mastodon instance. I get a lot of referral traffic from Mastodon, but each instance has its own URL. You can guess at mas.to, but dice.camp doesn’t provide many clues. Bubbles, as it’s known, is a very nice service. It aggregates a curated list of indie blogs. People can sign up and vote for posts they enjoy, but they can’t submit new articles. Authentication and comments are both handled using Fediverse technologies. In my case, I was able to log in via my Mastodon instance. The idea is to highlight cool indie writers around the web. I love this sort of thing so very much. Anyway, this is all to say that you should check out Bubbles. Seeing a blog-based reaction to one of my posts on the service filled my heart with immense joy.

I’ve been using Photoshop since the mid-90s. First at school, with Photoshop 3, then through work. I bought my first boxed copy of CS2 in 2005, then upgraded to CS5 in 2010. I subscribed to Photoshop Creative Cloud on day one. Today, I uninstalled it. I hope I never have to use Adobe software ever again. Photoshop used to be a joy to use. Whenever I got access to an upgraded version, I’d always have fun exploring the new features. I got really good at using it. When Adobe launched the Creative Cloud version of Photoshop in 2013, I signed up immediately. The subscription meant I would always have an up-to-date Photoshop, and I loved the idea that new features would be rolled out more frequently. But over time things started getting worse. Slowly at first, but then much more quickly. Originally, the Creative Cloud app was native and relatively useful. I wasn’t ever excited to open it, but I certainly didn’t mind having it installed. At some point, it became a terrible web-based app. Over time it felt slower and more broken. One thing I loved as part of the Creative Cloud subscription was the Creative Cloud Synced Files service. Basically, it was Adobe’s version of DropBox. I used it all the time to share screenshots and samples of in-progress work. Then, in 2023, Adobe announced they’d be discontinuing the service. There was so much pushback that they delayed the service’s retirement for a year. It makes sense, it was a nice feature of the subscription plan and businesses had come to rely on it. This was the first time I started questioning my Creative Cloud subscription. Out of curiosity, I looked around at the available options. I played with Pixelmator Pro, Acorn, and Affinity Photo. They were all fine, but I couldn’t let Photoshop go. I just knew it too well. But I also started realizing how little I was using it. I used to do a lot of traditional web development. In days of yore, this involved getting Photoshop mockups from designers. Those images needed slicing into pieces that you’d use to build a site or an app. But I hadn’t gotten a Photoshop document from a client in years. The PSD had been replaced with Sketch files, then with links to Figma documents. I still used Photoshop to touch up images, but that really didn’t use much of its power. The only thing holding me to the product was familiarity. Then I started to notice some real quality issues. For some reason that I still don’t understand, my copy of Photoshop stopped updating. I didn’t notice for a while, but eventually I stumbled upon the release notes and saw that I was something like nine months behind. I was able to fix this by forcing the Creative Cloud app to reload its settings using Command + Option + R, at which point I could update. Then, a few months later, Photoshop updates started getting stuck. I’d start an update, but it would spin for hours but never complete. I was able to fix this by uninstalling Photoshop using the Creative Cloud app, then re-installing it… but I had to do this more than once. Soon after that, every new Photoshop update would reset my preferences to the defaults. I’d need to take 5 or so minutes to re-apply my settings every time. A little while later, Adobe started silently updating my /etc/hosts file for license verification purposes. As posited in that link above, the Creative Cloud app now felt like malware to me. But that wasn’t all, Photoshop itself had started feeling terrible. There was now an annoying welcome screen that would re-appear for me whenever I didn’t have an image open. There was an option to disable it, but the option was reset every time I relaunched Photoshop for a couple of releases. Then Adobe decided to replace almost all of Photoshop’s native UI controls with web-based ones. This was the final straw. I’m sure some of these issues were special cases for me. Something that got stuck somewhere, maybe. I’m a developer, so maybe my tooling was interfering with something? Only: every time I ran into an issue, I’d see dozens of people complaining about the same thing on the Adobe support forums. It really felt like Photoshop and the Creative Cloud app had grown into blobs of pain that Adobe no longer knew how to properly maintain. As this was happening, Apple had released their Creator Studio service. For the same price as my Creative Cloud Photography plan, I could get an updated version of Pixelmator Pro, plus a bunch of other great apps. I’ve since signed up and haven’t looked back. But Adobe wasn’t done with me yet. It turned out that my subscription, which had been going since 2013, was on an “Annual Paid Monthly” plan. Even though I was getting billed monthly, I couldn’t actually cancel any time I wanted. I had sort of remembered this being a thing when I signed up, but had long since forgotten about it. Anyway, the one-month window to cancel without a termination fee recently arrived, and I got around to cancelling today. Cancelling required me to log into my Adobe account on the web. No problem, I thought. I had set up Adobe Authenticator, and had used it dozens of times to log in before. This time, however, the authenticator app needed me to log in. To log into the authenticator app, the app asked me to use the app to authenticate the app. Sorry? This was, of course, impossible. Eventually I figured out that I could use an alternative method to log into the app, so I could then use the app to authenticate my web session. This felt bone-headed, but whatever. I then received the following email. There’s nothing hidden here, this is the full contents of the message. At this point, though, I was actually able to start the cancellation process. The first screen of the cancellation flow looked like this: Here’s what it looked like after selecting things: I guess no one at Adobe uses dark mode? Anyway, the next 3 steps included Adobe begging me not to cancel, and even offering me three free months. This process had not convinced me I’d be happier staying. But even after completing the cancellation, I wasn’t done. I now wanted to uninstall everything. The Photoshop part of this was easy enough using the uninstaller app in the /Applications/Adobe Photoshop/ folder. The Creative Cloud app was more stubborn. There was also a link to an uninstaller for it in the /Applications/Adobe Creative Cloud/ folder… but running it failed with the error: Couldn’t uninstall Creative Cloud for desktop. You still have Creative Cloud applications installed on your computer that require it. Weird. The only other “app” I had installed was Camera Raw, which was just a plugin. There was also no way to uninstall it inside of the Creative Cloud app. I was able to find the plugin in /Library/Application Support/Adobe/Plug-Ins/CC/File Formats/. Deleting it and relaunching the Creative Cloud app showed that it was now no longer installed. I tried running the Creative Cloud uninstaller again, but I got the same error. This time I tried the “Repair” option, offered as part of the uninstaller, but that also failed. So I then tried the Creative Cloud Cleaner Tool… but this failed, too. At this point I was really annoyed, so I decided to manually remove things. I do not recommend doing this yourself, but here’s a general list of the stuff I got rid of: Under /Applications/: all the Adobe folders Under /Applications/Utilities/: all the Adobe folders The /Library/Application Support/Adobe and ~/Library/Application Support/Adobe directories, as well as any com.adobe.* files Under /Library/Preferences/ and ~/Library/Preferences/ all the Adobe* and com.adobe.* files Under /Library/Caches/ and ~/Library/Caches/ any Adobe* directories Under /Library/LaunchAgents/, /Library/LaunchDaemons/, and ~/Library/LaunchAgents/ directories: all the com.adobe.* files Under /Library/PrivilegedHelperTools: all com.adobe.* files Under /Users/Shared: all Adobe* directories Let me reiterate: you should not follow my lead here. I likely missed some things, and it’s very easy to mess things up by deleting system files. I offer no support if you decide to follow these steps. Again, it’s quite possible that there’s something weird going on with my machine or my installation… but I swear I never did anything but use the Creative Cloud app to manage things. I expect Adobe to be able to clean up their mess if they’re going to install files all over the friggin’ place. Anyway, all this said, I’m still slightly sad to be rid of Photoshop. Pixelmator Pro suits my current needs, but there are definitely things I will miss from Photoshop. Pixelmator Pro’s UI is a bit of a Liquid Glass nightmare, but it’s a massive improvement in terms of software quality. I’m extremely happy that it doesn’t strew zillions of files across my computer. I’m also pretty certain it will be much easier to unsubscribe from if I decide to do so in the future. So long, Photoshop. I’ll remember the old days fondly, but you are well past your prime.