> The problem arrises when Bob encounters a problem too complex or unique for agents to solve.
It’s actually worse than that: the AI will not stop and say ”too complex, try in a month with the next SOTA model”. Rather, it will give Bob a plausible looking solution that Bob cannot identify as right or wrong. If Bob is working on an instant feedback problem, it’s ok: he can flag it, try again, ask for help. But if the error can’t be detected immediately, it can come back with a vengeance in a year. Perhaps Bob has already gotten promoted by then, and Bobs replacement gets to deal with it. In either case, Bob cannot be trusted any more than the LLM itself.
> So if Bob can do things with agents, he can do things.
Yes, but how does he know if it worked? If you have instant feedback, you can use LLMs and correct when things blow up. In fact, you can often try all options and see which works, which makes it ”easy” in terms of knowledge work. If you have delayed feedback, costly iterations, or multiple variables changing underneath you at all times, understanding is the only way.
That’s why building features and fixing bugs is easy, and system level technical decision making is hard. One has instant feedback, the other can take years. You could make the ”soon” argument, but even with better models, they’re still subject to training data, which is minimal for year+ delayed feedback and multivariate problems.
That’s… one 9 of reliability. You could argue the title understates the problem.
> You don't need every single service to be online in order to use GitHub.
Well that’s how they want you to use it, so it’s an epic failure in their intended use story. Another way to put this is ”if you use more GitHub features, your overall reliability goes down significantly and unpredictably”.
Look, I have never been obsessed with nines for most types of services. But the cloud service providers certainly were using it as major selling/bragging points until it got boring and old because of LLMs. Same with security. And GitHub is so upstream that downstream effects can propagate and cascade quite seriously.
> And if this simpler solution was actually better for the company, it should be highlighted[…]
Simpler than what? The reason this phenomenon is so pervasive in the first place is that people can’t know the alternatives. To a bystander (ie managers), a complex solution is proof of a complex problem. And a simple solution, well anyone could have done that! Right?
If we want to reward simplicity we have to switch reference frame from output (the solution), to input (the problem).
I'm (also) an EM, I've been a pure EM in some roles in my career and I really struggle to understand these pain points that many people bring up. Isn't a manager job to know what their managees are focused on over a period of time? Shouldn't be they aware of the projects the team is working on? As EM and most probably previously engineers, shouldn't they know already why simple solutions are good?
Contrary to HN popular belief, there are neither incentives nor benefits to building native ui apps, for neither consumer nor professional apps. The exception is apps that only make sense on a single platform, such as window management and other deep integration. On iOS/macos you have a segment of indie/smaller apps that capture a niche market of powerusers for things like productivity apps. But the point is it makes no sense for anything from Slack, VSCode, Maya, DaVinci Resolve, and so on, to build native UIs. Even if they wanted to build and maintained 3 versions, advanced features aren’t always available in these frameworks. In the case of Windows, even MS has given up on their own tech, and have opted to launch webview based apps. Apple is slightly more principled.
Qt delegates to native UI in a lot of cases. I think a lot of people who rail against native UI fail to delineate between native UI and first party frameworks. Using third party frameworks, even cross platform ones, does not mean you lose out on native UI elements.
Strong disagree. I think Microsoft’s decision to wrap web apps for the desktop is one of the stupidest they have ever made. It provides poor user experience, uses more battery power and needs more memory and CPU to be performant and creates inconsistencies and wierd errors compared to native apps.
The increased adoption of webviews has resulted in a death by a thousand cuts effect on Windows 11 performance. The speed bump that comes from going from an up to date Windows 11 install to a up to date Windows 10 install on the same machine is stunning… W10 is much more snappy in every regard despite being nearly identical functionally speaking.
I won’t try to claim that Electron and friends have no place is software development but we absolutely should be pushing back harder against stuffing it everywhere it possibly can be.
Every modern desktop uses webviews in some capacity. macOS renders many apps with webviews, GNOME uses gjs to script half the desktop. The time to push back was 10-20 years ago, it's too late to revert now.
They’re still fairly uncommon in macOS, mostly being used in places related to cloud service settings. SwiftUI and Catalyst (iOS bridge) are both much more common than webviews, and AppKit remains ubiquitous.
Meanwhile on Windows major features like the Start menu are written in React.
Worth noting that WebKit webviews also tend to be more lightweight than their Chromium brethren.
What do you mean? With every launch they change the orientation of the camera array so you can tell who has the new model, and thus, is a better person.
You need to be well versed in the attribution for camera disposition. I am too old for that so getting understanding who is the better person is challenging :)
> Musk miscalculated on 1) cost reduction in LIDAR and 2) how incredible the human brain is compared to computers.
And, less excusable, ignorant of how incredible human eyes are compared to small sensor cameras. In particular high DR in low light, with fast motion. Every photographer knows this.
There are good arguments but this isn’t one. Many humans (like me!) drive fine without binocular vision. And the cars have many cameras all around, with wide angle lenses that are watching everything all the time, when a human can only focus in one direction at a time.
I thought only the front view has binocular vision on the cars. The others are single, with no depth perception. How does it know how close objects are outside this forward cone?
Is this true? I'm looking at a tree outside and I get parallax when I close one eye and then the other. I thought the parallax is the basis for depth perception.
> I should have the right to […] use a "free" store that is not under control of Google
Yes, but we also need to stop thinking like we’re trying to please the ghost of Steve Jobs. There is no ”store”. There are installers. You distribute them how you see fit, probably through the web.
These ”alternative stores” angle is a controlled dissent corporate plan B, much like how recycling was propped up by the fossil fuel industry.
> It feels like this has been completely lost, even on platforms like mac where consistency used to be important.
There are two kinds of consistency: across apps within a platform and across platforms within the same app. As someone who uses multiple platforms regularly, I have forever been annoyed when eg keyboard shortcuts change when I switch to a different computer, especially when I’m using the same app.
Apps like Discord, Spotify and VSCode are consistently the most pleasurable to use because they are largely the same.
For a unique piece of hardware like the old iPod, it made more sense to do your special custom UX as a unified product. But we’re talking about general purpose computers. The ”platform” shouldn’t be special imo, it should simply be predictable and stay out of the way. They mostly provide the same thing, like copy paste and maximizing a window, yet have different controls. This differentiation adds no value, at least to me.
You forget you’re a minority. Most users use one platform, or at most one work one private (probably with different software). So most software should be optimized for the platform, not consistency across them.
It’s actually worse than that: the AI will not stop and say ”too complex, try in a month with the next SOTA model”. Rather, it will give Bob a plausible looking solution that Bob cannot identify as right or wrong. If Bob is working on an instant feedback problem, it’s ok: he can flag it, try again, ask for help. But if the error can’t be detected immediately, it can come back with a vengeance in a year. Perhaps Bob has already gotten promoted by then, and Bobs replacement gets to deal with it. In either case, Bob cannot be trusted any more than the LLM itself.
reply