https://news.ycombinator.com/item?id=49867038

I went in expecting something handmade, and instead got something that was Claude-made. This doesn’t make me feel good, or feel user-centric. Now we’re throwing Blender into a webpage and serving it client-side rendered to users?

If anything, all of this feels more like bloat rather than something personal. It’s art for Claude’s sake. It’s not telling a story. Even on the actual blog post, the dropdown table of contents displays how long it takes to read each section. It feels so disconnected because it’s possible to throw a feature in, but is it really necessary? Maybe I am getting better at determining AI-made UIs, but all of this feels incredibly artificial.

Lastly, for all of the parallel QA checks and threads, all of the header links besides the “About” page throw a 404 at me. It’s almost ironic.

A great majority of business applications do run on open source projects, and in turn, are affected by them if things go awry. It’s a prisoner’s dilemma in this case.

Moving this to the backend with a templating engine still requires a formatted object, correct? I like SSR rendering, but I think the diagram with websockets is missing a key step, where the database results still need transformed into a consumable format that gets plugged into the templating engine. That step can’t get eliminated with either model.

Regardless of where the document is built, it needs to consume some format of structured data. Am I missing something?

https://youtube.com/@papapinball

It really isn’t doing any of that, though. When AI gets it wrong, that person needs to understand why it is wrong, and without that upfront knowledge or skill of reasoning, it’s much less direct to actually build something in the correct ways.

But for real, this is bad. Like, really, really bad. And I understand this could have been done before by just screenshotting an image from Google Maps and feeding into an AI image processor, but now, that whole process is streamlined and immediately available, and Google’s messaging is that we can just fact check it ourselves with another AI tool.

Well, that’s only possible with the original, non-altered image. Someone takes a screenshot and puts this up on a news broadcast or Twitter post, and then, how is anyone going to determine what is real or fake anymore?

Lastly, even with a private agent, being able to ask it for secrets and have it likely respond with them back is really, really, really bad.

Misconfiguration isn’t really the best word choice, either, because it’s definitely a both-sides problem.