The Emperor's New LLM • Hacker News Board

Re: The Emperor's New LLM

#61

Post by shmval » Sat, Jun 14, 2025, 8:56 PM UTC

wongarsu wrote: post #38

raincole wrote: post #32

Earlier quoted context omitted.

The problem is, no matter how you wrote the prompt, the way you wrote it still triggers some intrinsic bias of LLM. Even a simple prompt like this: = I have two potential solutions. Solution A: Solution B: Which one is better and why? = Is biased. Some LLM tends to choose the first option and the other prefer the last one. (Of course, humans suffer from the same kind of bias too: https://electionlab.mit.edu/research/…

Prompt writing can probably take a lot of lessons from designing surveys. Phrasing, the chosen options and their order have massive impact both for humans and for LLMs. The advantage with LLMs is that you can reset their memory, for example to ask the same question with a different order of options. With humans that requires a completely new human each time Half the battle is knowing that you are fighting

I think there's a lot of alpha left in building a better and more intuitive UX for seed/top-p/temperature etc. The vast majority of users don't get that far.

Re: The Emperor's New LLM

#62

Post by shmval » Sat, Jun 14, 2025, 8:58 PM UTC

nemomarx wrote: post #13

sysmax wrote: post #7

>The same kind of bias keeps resurfacing in every major system: Claude, Gemini, Llama, clearly this isn’t just an OpenAI problem, it’s an LLM problem. It's not an LLM problem, it's a problem of how people use it. It feels natural to have a sequential conversation, so people do that, and get frustrated. A much more powerful way is parallel: ask LLM to solve a problem. In a parallel window, repeat your question and the…

This feels like a pretty big ergonomics gap in presenting things as a chat window at all?

This. I think it's the key.

Re: The Emperor's New LLM

#63

Post by shmval » Sat, Jun 14, 2025, 9:00 PM UTC

api wrote: post #10

If you tell the LLM to criticize you, it will happily do that too.

Yes but you have to want that, and most people do not. Therein lies the rub.

Re: The Emperor's New LLM

#64

Post by shmval » Sat, Jun 14, 2025, 9:04 PM UTC

kazinator wrote: post #37

> they nod along to our every hunch, buff our pet theories That has not been my experience. If you keep repeating some cockamamie idea to an LLM like Gemini 2.5 Flash, it will keep countering it. I'm critical of language model AI also, but let's not make shit up. The problem is that if you have some novel idea, the same thing happens. It steers back to the related ideas that it knows about, treating your idea as a mi…

The trouble is there is a clear dichotomy in the scenarios where the LLM pushes back like this, most likely derived from RLHF. So anything health related, and "touchy" subjects in general will face this. But random design choices in your code, product roadmap debates etc do not elicit the same resistance.

Re: The Emperor's New LLM

#65

Post by danielmarkbruce » Sun, Jun 15, 2025, 4:34 AM UTC

eschaton wrote: post #45

danielmarkbruce wrote: post #33

Earlier quoted context omitted.

This idea that humans are so structured in their thinking is ridiculous.

It’s a whole lot less ridiculous—especially when discussed in a context where there’s an assumption that analysis is taking place—than attributing any sort of “thought” to LLMs at all .

"thought"... most of my "thinking" is done in language. The various intermediate steps of the latest reasoning models show something similar.