←back to thread

64 points todsacerdoti | 3 comments | | HN request time: 0.631s | source
Show context
anougaret[dead post] ◴[] No.43800305[source]
[dead]
1. godelski ◴[] No.43800481[source]
Are you saying that LLMs will generate shitty code and the fix that by using your LLM? That seems... inconsistent...
replies(1): >>43800650 #
2. anougaret ◴[] No.43800650[source]
we don't do the LLM part per say

we instrument your code automatically which is a compiler like approach under the hood, then we aggregate the traces

this allows context engineering the most exhaustive & informative prompt for LLMs to debug with

now if they still fail to debug at least we gave them all they should have needed

replies(1): >>43801081 #
3. godelski ◴[] No.43801081[source]
Okay this sounds better. But aren't there other continuous debuggers out there? It doesn't seem hard to roll my own. I can definitely get vim to run pdb in a buffer every time I save my file (or whatever condition). But this does seem quite expensive for minimal benefit. Usually people turn to print statements because it's easier than the debugger. Is it iterative so you don't do the full trace and only roll back your stack trace to where the breach occurs? That's much more complex

And critically, why are you holding my code for 48 hrs? Why is anything leaving my machine at all?