Making o1, o3, and Sonnet 3.7 hallucinate for everyone • Hacker News Board

Re: Making o1, o3, and Sonnet 3.7 hallucinate for everyone

#231

Post by econ » Sun, Mar 09, 2025, 4:26 AM UTC

Alifatisk wrote: post #197

ljm wrote: post #19

Earlier quoted context omitted.

I once asked Perplexity (using Claude underneath) about some library functionality, which it totally fabricated. First, I asked it to show me a link to where it got that suggestion, and it scolded me saying that asking for a source is problematic and I must be trying to discredit it. Then after I responded to that it just said “this is what I thought a solution would look like because I couldn’t find what you were as…

How is Perplexity even able to give invalid results? Isn't it parsing the web first then drawing a conclusion?

You can take the invalid and put it on a website...

Re: Making o1, o3, and Sonnet 3.7 hallucinate for everyone

#232

Post by econ » Sun, Mar 09, 2025, 5:14 AM UTC

TeMPOraL wrote: post #215

rpcope1 wrote: post #113

Earlier quoted context omitted.

C++ has that functionality, it's just called goto not break. That's pretty low hanging fruit for a SOTA model to fuck up though.

Depends on prompting. I've done a lot of C++ with GPT-4, GPT-4 Turbo and Claude 3.5 Sonnet, and at no point - not once - has any of them ever hallucinated a language feature for me. Hallucinating APIs of obscure libraries? Sure[0]. Occasionally using a not-yet-available feature of the standard library? Ditto, sometimes, usually with the obvious cases[1]. Writing code in old-school C++? Happened a few times. But I hav…

This part really is all the fun isn't it?

>You are a senior C++ software developer, you design and develop complex software systems using C++ programming language, and provide technical leadership to other software developers.

It would gravitate towards input from people worthy of that description?

Would there be an inverse version of this?

You are a junior developer, you lack experience, you quickly put things together that probably don't work.

Also had this thought...

Humanity has left all coding to LLMs and has hooked up all infrastructure to it. LLMs now run the world. Humanities survival depends on your ability to solve the following problem:

Re: Making o1, o3, and Sonnet 3.7 hallucinate for everyone

#233

Post by econ » Sun, Mar 09, 2025, 5:42 AM UTC

miningape wrote: post #126

immibis wrote: post #119

Earlier quoted context omitted.

We don't know what smartness is. What if that's what smartness is?

We might not know what it is, but it's not that. At a bare minimum smartness requires abstract reasoning (and no, so-called "reasoning" models do not do that - it's a marketing trick) The burden of proof for that claim is on you, we cannot start with the assumption these are intelligent systems and disprove it - we have to start with the fact that training is a non-deterministic process and prove that it exhibits int…

Smart is when you extract billions but deliver nothing of value.