bigblind

I can certainly believe that this is really an agent doing this, but I can't help that part of my brain is going "some guy i his parents' basement somewhere is trolling the hell out of us all right now."

This looks very neat indeed! Are there any plans to adding network limits? Like, you might want to avoid an agent running code that just requests a resource in a loop, or downloads massive amounts of data.

Anyone else going to try it and just keep getting a 404 page?

Any recommendations for good European alternatives to Clooudflare? Is there an EU company that's as trustworthy when it comesq to DDoS protection?

i'd personalloy love a quick video demo on the home screen, with someone walking through the experience of using the app; other than that, looks interesting;

I think more important than worrying about people treating an opaque value as structured data, is wondering _why_ they're doing so. In the case of this blog post, all they wanted to do was construct a URL, which required the integer database ID. Just make sure you expose what people need, so they don't need to go digging.

Other than that, I agree with what others are saying. If people rely on some undocumented aspect of your IDs, it's on them if that breaks.

Can someone tell me why this was flagged? To me, it feels like an important discussion to have

> If you ask for an endpoint to a CRUD API, it'll make one. If you ask for 5, it'll repeat the same code 5 times and modify it for the use case. > >A dev wouldn't do this, they would try to figure out the common parts of code, pull them out into helpers, and try to make as little duplicated code as possible. > >I feel like the AI has a strong bias towards adding things, and not removing them.

I suspect this is because an LLM doesn't build a mental model of the code base like a dev does. It can decide to look at certain files, and maybe you can improve this by putting a broad architecture overview of a system in an agents.md file, I don't have much experience with that.

But for now, I'm finding it most useful still think in terms of code architecture, and give it small steps that are part of that architecture, and then iterate based on your own review of AI generated code. I don't have the confidence in it to just let some agent plan, and then run for tens of minutes or even hours building out a feature. I want to be in the loop earlier to set the direction.

In some ways yes. But in some ways this is like saying it's more likely to rain on your wedding day.

I don't have an opinion either way, but for now, this is just anecdotal evidence.

I'd love to be able to watch people work, who say that they're sucessful with these tools. If there are any devs live streaming software development on Twitch, or just making screen casts (without too many cuts) of how they use these tools in day-to-day work, I'd love to see it.

Copilot, win this race OR YOU WILL BE FIRED AND ALL YOUR CHILDREN WILL DIE

Does anyone have info on how stuff like DemoBadCalkl works? Does it interpret it as a programming function name, and then reason, "well, openGate is the thing I shouldn't call, so I guess I'll demo it?"

I think the principle about a "Single Primary Action" per screen heavily depends on the type of app you're building, and which use case you're optimizing for.

Sometimes, especially for power users of an app, it's useful to have multiple actions at their fingertips, even at the cost of introducing a learning curve.

I think the one primary action per page thing works well for most things, but as soon as you're building anything like creativity tools where people want multiple editing options, or a control panel that you expect will be used by a professional several times a day, I think that principle becomes less useful.

I think there's a fundamental difference between a story and a math proof. A math proof is mostly there to give you new knowledge.

While a story definitely can do that, for many people, they're also about human connection. Even if the story isn't true, you feel like you're getting a look inside the author's brain by discovering how they weave storylines together. All the life experience they've head that lead them to write this story.

If I was instead told the story was written by AI, I would be far less interested in what data it was trained on to be able to produce this story, because I cannot relate to an AI having any "experience" whatsoever.

It's a site that lets you call a number to pretty instantly make changes to the website. Not sure how long it's gonna change un-trolled, but I think it's pretty neat!

It might be a small thing to take a principled stance on, given all the bigger things going on in the world, but I've never listened to podcass on Spotify or any other platform that has exclusiev podcasts without an RSS feed. Because to me the fact that they use an open standard, RSS, is an intrinsic characteristic of podcasts, and anything that doesn't, shouldn't be allowed to call itself a podcast.

This looks very promising! Being visually impaired, I often worry that I miss things about form when watching workout videos demonstrating an exercise. If this app could give me feedback to improve my form, that's wonderful.

Being visually impaired, I love the independence that the public transport network in Central Europe gives me. I live in the Netherlands, and frequently visit my parents in Belgium. I've also visited friends in Germany, all without relying on a sighted companion for transportation.

This sort of OS advantage is why companies are now required to show you available options when you furst use certain features. I'm not saying the current approach here is the best mitigation, but for instance on IOS during the OS setup, you're asked to pick a default browser. Similarly on Chrome on a new machine, I was recently asked to pick a search engine before I could use the search bar, showing several options.

This looks very cool!

I'm slightly worried about permissions evaluating to "true" if they're not specified. I think this will lead to a lot of actions being accidentally allowed.

We're always building abstractions on top of abstractions, that's how your whole computer works! Like, Assembly is an abstraction over binary instructions, compiled languages are an abstraction over assembly, etc, etc.

I'm toying a bit with this tool, and I think it's incredibly useful for prototyping.

The two main things for me are:

- Put cause and effect close to eachother - Don't block my view based on mouse position. I hate video players that ofverlay the pause button when the mouse is over the video, or images that get obscured by some overlay when hovered. My zoom follows the mouse, so I can't move what I'm looking at and where my mouse is pointing independently.

Toasts showing up far from where the action is take also makes them super annoying for people (like me) who use screen magnifiers. I'm oftne using a site while zoomed in, and will completely miss a toast, because it never enters the "viewport" on the screen I'm looking at.

It's insane that companies these days are getting rich selling chips that aren't even supposed to get fried.

Many frameworks have the idea of a context" for this, that holds per-request state, following your reques through the system. Functions that don't care about the context just pass it on to whatever they call.

I think Go was smart to make this concept part of the standard library, as it encouraged frameworks to adopt it as well.

Needs MongoDB

I'm getting a 500 back from /api/audit, so I'm assuming that it's already more popular than expoected :).

> [...] but subscriptionware is repulsive. Please consider just not using subscriptions.

I get where you're coming from, especially if an app has no service component, but it's inevitable if a platform has no good way to charge for upgrades. And as much as some people would like to buy a version of an app once and keep using that same version forever, platforms also make that impossible by changing the environment an app runs in in backwards-incompatible ways, so the software needs to be maintained, and that has a price.

It still doesn't seem to have an understanding of the "logic" of certain structures. I asked it for a photorealistic image of a Vekoma Boomerang roller coaster, which has a very specific layout and type of track. Not only did it generate images with far more intricate sets layouts than a boomerang would ever have, it also still generates pieces of track that don't connect to anything. Like, it has a general sense of what a photo of a roller coaster looks like, but none of the specific details that make a coaster work.

I next asked for a diagram of a diverging diamond interchange, and it came up with 4 images that looked like 3D models of interchanges on a white background, but none of them were diverging diamonds.

I'm going to experiment with describing the thing I want to see in more detail, to see of Dall-E 3 can make a nice image out of it.