logoalt Hacker News

causal • today at 1:23 PM • 8 replies • view on HN

I wonder if someday we will get to the point where Github repos are just markdown files describing the project and then you just let your own agent implement it because why the hell would I trust your agent's implementation?


Replies

jaggederest • today at 5:11 PM

Here's a couple examples, I've seen others as well:

https://github.com/seb3773/ntfs-repair-rfc

https://github.com/Kotivskyi/screenshot-tool

I think it was more popular around the beginning of the year to mid-year

nater5000 • today at 2:57 PM

Seriously. I imagine this will be the case soon enough in some shape or form.

Whenever I see these vibecoded apps, my move is to just do what you've described: point an agent at it and tell it to reproduce it (usually with my own little customizations). It's a bit absurd, but I don't trust that they vibecoded the app as well as "I" could lol.

➕ show 4 replies
theropost • today at 3:33 PM

Isn't it already kind of like that? Except the agent reads the code as if it's markdown. There's really no difference anymore, is there?

asdff • today at 5:21 PM

With enough model drift that won’t even work over time. These files would have to be pinned to the intended model version and that is either used directly or emulated with a faithful emulator in a larger model.

➕ show 2 replies
glitchc • today at 4:38 PM

Sounds like Github is optional at that point. Why not just use Medium or WordPress?

➕ show 2 replies
m-s-y • today at 4:13 PM

ding ding! we have a winner!

fennecfoxy • today at 3:40 PM

Eh I think it'll be more like Gibson's defensive ICE in that ICE is "my swarm of agents scans your code for nasties, then compiles it from source".

➕ show 2 replies
cyanydeez • today at 1:31 PM

if all your models are in the cloud, why would you trust anything your agent builds

➕ show 1 reply