News for hackers. Stuff that matters.
Re:Claude Code is all you need by kenjackson on Monday August 11, 2025 @07:00PM (#44870421)
What was the simple function?
Re:Claude Code is all you need by pron on Monday August 11, 2025 @07:56PM (#44870836)
Can't remember, but it was something very basic - a 10/15-line routine that a first-year student would write in 3 minutes if they knew the relevant API. The reason I asked the model in the first place is because I didn't know the API. If memory serves, the model inverted an if or a loop condition.
Re:Claude Code is all you need by p1esk on Monday August 11, 2025 @09:05PM (#44871225)
Did you use one of the latest frontier reasoning models? If not, how is your experience relevant?
Re:Claude Code is all you need by totallykvothe on Tuesday August 12, 2025 @12:36AM (#44872455)
In what world is this an appropriate thing to say to someone?
Re:Claude Code is all you need by guappa on Tuesday August 12, 2025 @03:10AM (#44873287)
In the creed of "AI is perfect, if you claim otherwise you're broken" that so many here embrace.
Re:Claude Code is all you need by p1esk on Tuesday August 12, 2025 @02:04PM (#44879806)
In the world where you do not claim that LLMs suck today based on your attempt to use some shitty model three years ago.
Re:Claude Code is all you need by jama211 on Tuesday August 12, 2025 @01:34AM (#44872750)
So you tried it once and then gave up?
Re:Claude Code is all you need by pron on Tuesday August 12, 2025 @06:49AM (#44874630)
I didn't give up, I just know that I can only use a model when I have the patience to work with something I can't trust at all on anything. So that's what I do.
Re:Claude Code is all you need by jama211 on Tuesday August 12, 2025 @03:32PM (#44880868)
Sounds like the spirit of my question remains intact
Re:Claude Code is all you need by throwaway31131 on Monday August 11, 2025 @07:33PM (#44870683)
I’m not sure what their simple function was but I tried to use Claude to recreate C++ code to implement the algorithms in this paper as practice for me in LLM use and it didn’t go well. But I’ll be the first to admit that I’m probably holding it wrong.

https://users.cs.duke.edu/~reif/paper/chen/graph/graph.pdf