Live data from Hacker News

NanoClaw's architecture is a masterclass in doing less

jonno.nz

11–14 of 14 posts

Re: NanoClaw's architecture is a masterclass in doing less

#11
post #5

Unfortunately this has all the hallmarks of AI writing, which made me a lot less motivated to read it.

yeah me too. It's a shame because I'm sure the content of it is very precise when it comes to the technical data. It is just that, if this post has been made to be consumed by other humans, it would be better written from the experience and intepretation of another human being. It is a blog post, not a science investigation or law document

Re: NanoClaw's architecture is a masterclass in doing less

#12
post #5

Unfortunately this has all the hallmarks of AI writing, which made me a lot less motivated to read it.

yeah me too. It's a shame because I'm sure the content of it is very precise when it comes to the technical data. It is just that, if this post has been made to be consumed by other humans, it would be better written from the experience and intepretation of another human being. It is a blog post, not a science investigation or law document

The next one linked at the bottom, https://jonno.nz/posts/stealing-nanoclaw-patterns-for-webapp... has this bold and frankly unbelievable claim:

"70% of startups fail due to premature scaling"

.. which is a link to another blog post somewhere else that says nothing even slightly related.

Re: NanoClaw's architecture is a masterclass in doing less

#13

The "permissions as access/visibility" is unfortunately not holding up in practice. As nice as a simplification like this would be: No one wants to configure up front what permissions are needed. Users will run into annoyances and then just overcommit resource access the same way they choose to run yolo mode. Limiting access for security is a great part of a capability based system but a system that will be used in t…

> web proxy

do you know of a mitm proxy that "just works"? meaning, is able to spoof/intercept/modify running processes well enough that most stuff would run without manual modification?

Re: NanoClaw's architecture is a masterclass in doing less

#14
post #13

The "permissions as access/visibility" is unfortunately not holding up in practice. As nice as a simplification like this would be: No one wants to configure up front what permissions are needed. Users will run into annoyances and then just overcommit resource access the same way they choose to run yolo mode. Limiting access for security is a great part of a capability based system but a system that will be used in t…

> web proxy do you know of a mitm proxy that "just works"? meaning, is able to spoof/intercept/modify running processes well enough that most stuff would run without manual modification?

There are tons that are all too simple or too complex or made for mesh networking in k8, or too slow and made for debugging. My go-to solution is to make ad-hoc proxies with workerd that work just the way i need and compile to a "binary". It used to be annoying to write capnp by hand but now you just point an agent at worker.capnp and tell it what you need. The output is concise enough to be nice for proper reviewing and as extendable starting point, so neither vibe coding nor much manual coding needed.
Post reply on HN