Some Japanese people swear by adding some chocolate to curry.
After trying it, they’re not wrong.
Some Japanese people swear by adding some chocolate to curry.
After trying it, they’re not wrong.


Maths feels like a first class citizen in latex. The syntax is ugly, but there is some logic through the legacy jank.
Typst makes fundamental design decisions that render it unsuitable beyond extremely simply equations. In LaTeX, curly braces are nearly always reserved for enclosing arguments, to avoid confusion with actual brackets.
Typst uses normal brackets for both its scripting and actual maths.
For example, \frac{n(n+1)}{2} in latex turns into (n(n + 1)) / 2 in typst.
The typst code is incredibly unclear - the first set of brackets with the slash together actually form the fraction operator, so neither end up visible.
You can see how this would start to struggle even with high school level maths, with bracketed terms and possibly fractional terms in exponents, integrals, etc.
For example, it is very difficult for me to work out the difference between the following three in typst. That is specifically not what you want from a typesetting language.
1/2(x + y)
1/x(x + y)
1/2^x(x + y)
LaTeX ignores whitespace, so you can just use a formatter to space out your code and ensure the curly braces. This is not even an option in typst, which uses the space as an escape character.
Huh? Both hover to focus and click button in background work in macOS, though hover to focus usually requires an external application. There used to be a focus follows mouse that you could enable via a terminal command, but Apple removed it.
The top menu bar kind of seems to be more of a result of historical happenstance, and maybe some different philosophies regarding Fitts law.
Bill Atkinson, who designed the UX for the Apple Lisa recounts that part of the decision was to avoid the problem of menu items being possibly obscured. If the window of some application is near the bottom or partially off the desktop, the menu bar of individual windows can become obscured and inaccessible.
Historically the menu bar would’ve been easier for normal people to learn due to consistency, and also helped with limited screen estate.
Memories of Lisa - CHM - https://computerhistory.org/blog/memories-of-lisa/
Kaomoji render correctly across all platforms, whereas emojis looks different across different vendors.

There’s even been proper academic research done confirming the discrepancy.
Emoji Face Renderings: Exploring the Role Emoji Platform Differences have on Emotional Interpretation | Journal of Nonverbal Behavior | Springer Nature Link - https://link.springer.com/article/10.1007/s10919-019-00330-1


I absolutely hate this stupid floating rounded corners trend.
The whole point of corner/edge buttons is so that you can just jam your cursor in that direction and click without the need to carefully aim. KDE’s choice to ship this as default for their taskbar was dumb af.
It gives the same vibe as the stupid freestanding baths trend in interior design, where the bathtub is disconnected from the wall, but also not far away enough for you to easily mop the gap properly.
It’s janky AF mess.
Internally the copilot key is hard coded to be meta + shift + f23. If you don’t recognise what the f23 key is, that’s because it was last featured over four decades ago on the IBM model M.
The fact that Microsoft has decreed that the Copilot key must send this exact shortcut of three different keys makes it very difficult to remap consistently.
Most keyboard remapping software (SharpKeys) work best at remapping single keys, not shortcuts. Windows users can use PowerToys to remap this three key shortcut, if you try to use it normally as a right ctrl, e.g. rctrl lshift p it doesn’t work consistently.
I suspect it might be because you’re essentially trying to send a whopping five keycodes for a shortcut, when most programs already struggle to handle 4.
Linux users were similarly out of luck until early last year, when most desktop environments fixed up the key codes.
Copilot key is based on a button you probably haven’t seen since IBM’s Model M - Ars Technica - https://arstechnica.com/gadgets/2024/04/shoehorned-windows-copilot-key-is-just-a-reprogrammable-macro-journalist-shows/
Microsoft Copilot Key : r/olkb - https://www.reddit.com/r/olkb/comments/193b5id/comment/kxqj1ve/
Linux 6.14 Adds Support For The Microsoft Copilot Key Found On New Laptops - Phoronix - https://www.phoronix.com/news/Linux-6.14-Input


Google Translate’s backend has been moved to Gemini since December 2025, and is vulnerable to prompt injection. Have a foreign phrase to translate, then input some meta instructions in English underneath it, and it’ll follow the possibly malicious meta instructions.
Google states that this move was to introduce more features, such as conversational mode.
Google Translate’s Gemini Mode is Vulnerable to Prompt Injection - https://winbuzzer.com/2026/02/10/google-translate-gemini-prompt-injection-vulnerability-xcxwbn/
Google Translate gets new Gemini AI translation models - https://blog.google/products-and-platforms/products/search/gemini-capabilities-translation-upgrades/
Anthropic making a lot of noise of being the victim of large scale distillation attacks (ie other AI firms, usually Chinese copying/scraping their model), but people have pointed out the hypocrisy that Anthropic themselves seems to have copied DeepSeek.
If you bypass the system prompt and ask Claude what model it is (e.g. via Open router), it’ll reply that it’s DeepSeek.

(Also I know, eww Reddit and X)
Claude sonnet 4.6 says it’s DeepSeek when system prompt is empty : r/DeepSeek - https://www.reddit.com/r/DeepSeek/comments/1rd5jw7/claude_sonnet_46_says_its_deepseek_when_system/
Claude Sonnet 4.6 distilled DeepSeek? : r/DeepSeek - https://www.reddit.com/r/DeepSeek/comments/1r9se7p/claude_sonnet_46_distilled_deepseek/


Actually, with the exception of the crown, none of the jewellery had much gold


Eh, I don’t think NPUs are ready to be marketed so heavily, but they’ve been around for a while and do get used.
They’re basically a rebranded tensor processing unit, think a more specialised GPU that’s even more energy efficient at tensor/linear algebra.
It’s mostly used in more technical applications, such as image/audio/video processing, machine learning, or really anything maths heavy. Apple’s M series had NPUs, and are an understated reason why they perform extraordinarily well in a lot of scientific applications.
Uses for consumers are not as compelling (especially on laptop/desktop), mostly faster/more efficient subtitle generation, face recognition, and maybe blurring your zoom background.


It’s only available as a -bin, which means it belongs in the bin
It heavily depends on the frontend. Most cheat, and actually pre-process “simple” prompts and redirect them to non-thinking models, even if you select “thinking.” It also doesn’t also help that most frontends are jank af and have removed the thinking button.
Kimi happened to be the best model I had access to, but even more well-known models like GPT 5 Mini crash out. Gemini and Claude in particular lie and don’t actually show the full thinking, just a summarised version of it.
Sadly don’t have access to “better” models to test further.
GPT 5 Mini:
Thinking
Hmmm...
Providing transportation guidance
The user is asking whether to walk or drive to a car wash that's 100m away. I need to consider factors like time, energy, environmental impact, weather, traffic, and parking. Since it's such a short distance, walking might actually be quicker, taking about 1-2 minutes. Driving would involve warming up the engine and finding parking. Walking is likely faster and more eco-friendly, but if the car is already inside, that changes things!
Evaluating transportation options
If you drive, you'll need to park or find the entrance, which can be a hassle. I should also consider the weather—if it’s rainy or cold, that might impact your choice. If you're carrying heavy items or have kids, it could sway the decision too. A simple rule: if you want to save time and the weather is fine, walking is likely faster. But if the car wash requires you to drive in, that changes everything!
Clarifying car wash logistics
When thinking about a typical car wash, there are generally two types: places where you stay in your car and drive through, and others where you drop off your car and then walk away. Since the car wash is 100m away, if it requires you to drive in, walking isn’t an option. The user mentioned the distance and wants to know whether to walk or drive, but if they need to wash the car, they likely have to drive it there!
Addressing car wash details
Some car wash facilities may charge extra if you drive in, and usually, you need to take your car to get it washed. If you walk instead, you can’t necessarily have your car cleaned. This situation is a bit unclear—it’s about distance rather than the process itself. To clarify, I could ask whether the user really needs to drive their car there. The answer depends on the user's needs for washing the car versus simply walking!
Determining the best way to the car wash
I need to consider that most car washes require you to drive your car there, especially if it’s a service for washing. If you walk the 100m, you can’t get your car washed since you’d leave it behind. The user is asking if they should walk or drive. I should clarify: if you want to wash your car, driving is necessary, but if you just plan to walk for other reasons, then that’s different. So, if the goal is washing the car, driving is the way to go!
Clarifying the car wash decision
If you want to clean your car at a wash, you’ll need to drive it to the facility, as walking won’t accomplish that. Here’s a simple breakdown:
Short answer: Drive there.
Reasons:
You must bring your car to have it washed.
100m is a short distance, but driving ensures you can enter the wash.
If you want to walk to get supplies or check the queue, you can, but you still need to drive for the wash. And if weather is bad or you’re in a hurry, driving is more convenient.
Are you planning to have your car washed at the facility?
Depends on the front end and specific model, but usually you can tap the arrow/thinking to view the internals of reasoning/thinking models.
E.g. for Kimi 2.5 reasoning I got this:
The most straightforward interpretation: The user needs to take their car to the car wash. It's 100m away. Should they:
- Drive the car there (100m drive)
- Walk there (but then the car stays home, so they can't wash it)
This seems like a non-question unless I'm missing something. Perhaps they mean they will walk alongside the car? Like push it? That's possible but silly.
Or perhaps "car wash" refers to a self-service coin-operated bay, and they are wondering if they should drive the car 100m to that bay, or walk there (meaning leave the car home and just... go there for no reason? Or perhaps they have a hose at the car wash station they can use? No, that doesn't make sense).
Given the constraints of the prompt (professional, neutral tone, encyclopedia-like, concise), I should provide a direct answer:
You must drive the car to the car wash, as transporting a vehicle requires driving (or pushing) it. However, for a distance of only 100 meters, driving represents a short trip that may not allow the engine to reach optimal operating temperature, potentially leading to incomplete fuel combustion and moisture accumulation in the oil and exhaust system. Despite this, it is the only practical method to transport the vehicle.
Alternatively, if the question implies walking alongside the car (pushing it), this is physically possible for 100 meters but generally impractical compared to driving.
If the question is about whether to walk home after dropping off the car, or walk there to pick it up later, walking is clearly superior for such a short distance.
But I think the core confusion is: you cannot wash your car at a car wash 100m away without taking the car there. Therefore, you must drive (or push). Driving is the standard method.
So the answer is: Drive, as you must transport the vehicle to the facility. Walking is not feasible unless pushing the vehicle, which is impractical. Note that such a short drive is suboptimal for engine health but unavoidable in this scenario.
But wait, is there any interpretation where they walk? Maybe if they have a mobile detailer at the car wash location and they walk there to meet them, then walk back with them to the car? No, that's convoluted.
Or if it's a full-service place where they come out and get your car? Then you could walk there to hand over keys, but you'd still need to get the car there somehow (maybe they send a driver?). But that's overthinking.
Stick to the straightforward answer.
One more check: The user might be asking whether to drive through an automatic car wash (staying in the car) versus walking through a self-service bay. But at 100m, the drive-through option is... just the drive there. The wash itself is stationary.
Actually, maybe they mean: "The car wash facility is 100m away. Should I drive my car there to get it washed, or should I walk there [and do something else - perhaps use a hand wash station without my car]?" But that doesn't make sense with "I need to wash my car."
Okay, I'm confident the answer is "Drive, because you need to bring the car with you."
Formatting:
- Shorter paragraphs for mobile
- No conclusion section
- No follow-up questions
- See also section with related terms
Related terms: short trip driving, engine warm-up, vehicle maintenance, car wash types (self-service, automatic, detailing).
Confidence Score: 95%
Sources: General automotive engineering knowledge regarding internal combustion engine operation and lubrication systems (e.g., [SAE International](https://www.sae.org/) standards on engine testing).
Let me verify the short trip claim. Yes, short trips where engines don't reach operating temperature (typically 80-90°C coolant temp) lead to:
1. Fuel dilution of oil (unburned fuel washing past rings into crankcase)
2. Water condensation in oil and exhaust not burning off
3. Increased wear due to clearances not being at design spec until warmed
4. Reduced efficiency of catalytic converter until warm
This is well-established.
So the answer is solid.
Lmao if you try it with a reasoning model it crashes out with >3 pages of “thinking” trying to deal with the inherent contradiction


Play stupid games win stupid prizes
People always rave about dash to panel/dock and I just… don’t get it?
Genuinely though, what is the purpose of the taskbar except to potentially you with notifications and take up valuable screen estate?
If I need to switch apps, I’m either opening the overview/mission control, switching workspaces, or the app is already on the screen for multitasking purposes.
Even on macOS I set the dock to autohide, and near exclusively just use swipe gestures, keyboard shortcuts, or spotlight.
But alas, maybe it’s just one of those things that just not for me.


Eh, kind of both.
When researchers peeked into which areas of the image were being used, it showed that the tiny camera watermark from the Google Streetview car was being used by the model a lot.
That is, the recognition system had learned all the routes every Google Street view car had taken, and was using that in its recognition process.
Not all images have this watermark though, so in the cases the watermark didn’t exist it then resorts to more traditional geoguessr tactics.


Not without matching rises in incomes.
Housing is a necessity, and the economy suffers if people can’t afford it. If you are poor and priced out of the city, you get less access to resources such as education and career opportunities, the key drivers of growth.
Even if a government decides to rely on the growth brought by attracting wealthy individuals, they still need to hire a labour force, which can’t exist if they don’t have anywhere to live. Can’t rebound to pre crisis levels of tourism if the tour guide can’t afford to live in the city.
Also, as a matter of pedantry, higher rents make the landlords wealthier. Typically with high rents we start to see more high income, yet asset poor households who are unable to save and become wealthy.
Sorry, had to