For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | kordlessagain's commentsregister

Those vulnerabilities were found by open models as well.

Partly true. I think the consensus was it wasn't comparable because Mythos swept the entire codebase and found the vulnerabilities, whereas the open models were told where to look for said vulnerabilities.

https://news.ycombinator.com/item?id=47732337


Not really. The models were pointed specifically at the location of the vulnerability and given some extra guidance. That's an easier problem than simply being pointed at the entire code base.

Surely the Anthropic model also only looked at one chunk of code at a time. Cannot fit the entire code base into context. So supplying an identical chunk size (per file, function, whatever) and seeing if the open source model can find anything seems fair. Deliberately prompting with the problem is not.

This is pretty much correct, but Mustafa Suleyman has probably been doing it longer.

I have a clue, a big one, and do 100% vibe coding. Stop splitting hairs.

if you had a clue you would not be doing 100% vibe coding :)


And massive VM drive growth

No CLI installer for Windows.

App itself for Windows won't proceed past my selected repo. Said something about bad permissions, but I use that repo every day.


Don't do that. Don't buy into the bullshit.

Nobody said anything about an API with thousands of endpoints. Does that even exist? I've never seen it. Wouldn't work on it if I had seen it. Such is the life of a strawman argument.

Further, isn't a decorator in Python (like @mcp.tool) the easy way to expose what is needed to an API, if even if all we are doing is building a bridge to another API? That becomes a simple abstraction layer, which most people (and LLMs) get.

Writing a CLI for an existing API is a fool's errand.


Cloudflare wrote a blog post about this exact case. The cloud providers and their CLIs are the canonical example, so 100% not a strawman.

> Writing a CLI for an existing API is a fool's errand.

I don't think your opinion is reasonable or well grounded. A CLI app can be anything including a script that calls Curl. With a CLI app you can omit a lot of noise from the context things like authentication, request and response headers, status codes, response body parsing, etc. you call the tool, you get a response, done. You'd feel foolish to waste tokens parsing irrelevant content that a deterministic script can handle very easily.


I deploy to Google just fine with Claude and have ZERO use for Cloudflare's toxic code.

Anything that says goodbye to Cloudflare man-in-the-middlinging is joy to my big ears.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search:

HN For You