yuedongze

This, and I would even say we are promoting people to be kings and queens. I'm afraid AI will amplify our worst parts because they are ultimately sycophants. I've heard so many things about AI enabling a single person to run a billion dollar business. But I believe without the right mindset/discipline, a person cannot go too far with any technology.

AI doesn't automatically make us better human beings, but they only expose our worst parts. Most people are not born great leaders and managers (need rigorous training and experience), and empowering them with AI kind of pushes them into a spot where they suddenly need to "lead". To fight brainrot from AI overuse, we must try harder to maintain that developer's priority list.

Very cool! will feed this to Claude today and see how it works. The "Get Started" button on the landing page doesn't work though, looks like a small navigation bug.

Try this HN clone and click around. Everything is vibed by AI in real time.

prompt: front page of hackernews however in a staggered grid layout as a vertical scrollable feed, as a mobile app, using real hackernews API. for each post have a way to go to the discussions page

another version i liked: https://vibes.higashi.blog/pages/c72c3d3e-2935-4b8a-8d71-dd0...

Ultimately, I'd like to go for the experience of - if I want an app, instead of downloading an existing one, I just go there and vibe one, and I can use it right away, like perhaps a calculator, a world clock, a note pad, or prototyping an app idea. The page gets torn down right after each use, or you can create a link to make it reusable/sharable for a certain duration.

But it's really about making vibe products disposable and responsive that I think it will make our experiences with AI app builders a lot better.

haha yea i got tired of waiting and wanted to see things coming to life. interestingly there is another HN post right above this one that asks what people do when waiting for LLM response. hopefully we dont need to wait!

it's very similar to the verification engineering problem i wrote about on HN last week. AI is as good as we can prove their work is genuine. and we need humans in the loop to fill in the gaps between autonomous systems and ultimately be held accountable by human laws. it's kind of sad but the reality we are facing

because it looks about right to me

this is something one can look in further. it is really probabilistic checkable proofs underneath, and we are naturally looking for places where it needs to look right, and use that as a basis of assuming the work is done right.

It's nice to see a wide array of discussions under this! Glad that I didn't give up on this thought and end up writing it down.

I want to stress that the main point of my article is not really about AI coding, it's about letting AI perform any arbitrary tasks reliably. Coding is an interesting one because it seems like it's a place where we can exploit structure and abstraction and approaches (like TDD) to make verification simpler - it's like spot-checking in places with a very low soundness error.

I'm encouraging people to look for tasks other than coding to see if we can find similar patterns. The more we can find these cost asymmetry (easier to verify than doing), the more we can harness AI's real potential.

I think it's definitely an interesting subject for Verification Engineering. the easier to task AI to do work more precisely, the easier we can check their work.

indeed, i see verification debt outweighing tradition tech debt very very soon...

oh i mean the other direction! checking if a generated image is "good" that no one will tell something is off and it look naturally, rather than checking if they are fake.

i've seen a lot of startups that use AI to QA human work. how about the idea of use humans to QA AI work? a lot of interesting things might follow

im hoping this can introduce a framework to help people visualize the problem and figure out a way to close that gap. image generation is something every one can verify, but code generation is perhaps not. but if we can make verifying code as effortless as verifying images (not saying it's possible), then our productivity can enter the next level...

oh interesting thoughts! let me digest and get back to you. overall i just defined a read API description that is "read content from this gist file by calling this API, it returns content of a text file, formatted as CSV, with first row defining the columns" and a write API description that is similar.

I develop on a paid plan GPT-4o (it allows me creating custom GPTs), but users can be on free tier GPT-4o to use it (although it limits image uploads to a handful per day). free tier github as always.

I’m curious who is willing to use more than 10 clouds

The HTTP/S proxy network of NL is interesting. But I think QUIC unreliable transport + MASQUE is the future here

Are there any good performance tests done between Tinc and WG? Curious to see how they perform and what there bottlenecks are.

I feel that this kind of competes with Tailscale and all the other connectivity providers all of sudden…

Learning curve is real difficult

One thing I value the most is the combination of markdown and latex support, plus mermaid diagrams. It’s very hard to find something that works super well on everything. Right now a customized Hugo with KaTeX is the best solution, but I’m still sad I cannot use MathJAX :((