YHK - yet another hacker news clone

"anti-ai"

> https://github.com/DilawarShafiq/nietzschian-debugger#setup

Step one to setup: "Set your Anthropic API key"...

README.md says:

> The anti-AI.

but then it's an AI-generated picture of Nietzsche [1] and AI-generated README with AI-generated code (Claude being the co-author), and when I read sample transcript e.g. in (nietzschian-debugger/tests/fixtures/sample-sessions/sample-v1.json) it's clear the app also uses LLMs to generate output...

So what do they mean by "anti-AI"?

[1]: All issues with AI-generated images aside, AI-generating a person's likeness seems like the rudest way to do this... At least use an actual photo/drawing of his...

Even Anti-AI tech now uses AI. How far we have come!

Unfortunately, in <current year> "AI" seems to mean "chatbot assistant". So, by "anti-AI" the author meant "the thing that acts the opposite of how you would expect a helpful chatbot to act".

Yes, I hate this usage of the term "AI" too.

Could be just use a skill i think

The irony of naming this Nietszche's Debugger when he, Nietszche, directly attacks the Socratic dialectic in the Twilight.

I was thinking Adorno's negative dialectics would be a better, if gloomy, fit; debugging is never-ending.

If you're in a positive or hopeful mood, or still a junior dev, Hegel's determinate negation offers reconciliation and an ending. This is a phase; dear junior devs you too will eventually share the Adornian resignation.

The anti-AI debugger, built with AI.

Could this not have just been a skill?

Nietzsche had no qualms with asserting answers. If anything this should be named after Socrates. But then Socrates would have despised AI for its automation of thinking. Really this Claude project shouldn't be named after philosophers at all.

I see how this could be useful, to roast agents while they are debugging or building something.

Home. java:2: error: <identifier» expected Public static void main (String[] arg){ ^ Recursion error: void main gazes back

I love the idea of helping people learn good debugging habits and understand their code. But this seems like it is still just giving the answers, and would still create the same dependence on AI to do your thinking:

  You: I'm not sure, it seems random

  Nietzschian: "Random" is the word we use when we haven't looked
  hard enough. What do the server logs say for the 403
  responses? Go look. I'll wait.

That move from "I don't know" to "where could I look to find out" is one of the key habits that makes someone good at debugging, and here "Nietzsche" is just doing it for you.

It might seem obvious to look at the logs, but in my experience 90% of being stuck debugging something is just not yet having looked at all the available evidence.

It's true you could learn these habits by exposure to them, and this could be a neat alternative to pairing with a more senior engineer for that. But it looks like you could easily just keep saying "it's random", "I don't know", and the model would keep telling you what to do next, without you actually having to think.

I wonder if making it even more Socratic would fix this? E.g. "how do you know it's returning 403s? Oh, logs you say? Is there anything else they could tell you?"

The biggest problem with having an LLM do this, from what I've observed of at least frontier models, is that the way they are trained/forced to behave makes them do one of two things, neither of which is educational or helpful:

1. They ask you a "hard question" but then immediately give you some kind of "hint" which makes it obvious what the "answer" is (or, even worse, they just tell you what it is).

2. They get pedantic (and I mean maximum emphasis on the word), to the point that they will nitpick the exact, precise wording you use, even if the context makes it blatantly obvious what you meant. GPT is currently the biggest offender in this area (it is ridiculously pedantic even though I haven't told it to be so).

And yes, in case anyone is wondering, I do actually read the output of tools like Claude and I have tried, repeatedly, to get them to do something like this, and one of the two aforementioned things always happens for some reason. I'm not sure if this is a problem with how they were trained, an issue with their system instructions, or what.

Cool idea, Nietzsche or not. Curious if one could just boil this down into a skill or prompt for better portability though. May give it a try.

A markovian prussian rubber duck?

This is pure dev astrology, but in the subsidized Sonnet 3.5 times in copilot I'm guilty of prompting 'You're Uncle Bob make this legacy java services read like a book top down with the cleanest code' just for fun and I might have learnt something and had some fun so I'm not judging.