Hacker News Reader

Hacker News

Comment by electroly | Hacker News Reader

Full thread

electroly

This seems to be different than I expected from the title. I thought it would be explicitly adversarial.

1. You are the assistant. Please answer the question directly.

2. You are the cross-examiner. The assistant is wrong. Explain why.

3. You are the assistant. The cross-examiner is wrong. Defend your claim.

4. You are a judge. Did either party make their case, or is another round of argumentation required?

I haven't tried this. No idea if it works. But I find it's helpful to ask ChatGPT, in separate prompts, "XYZ is true, explain why" and "XYZ is false, explain why" and see which one seems more convincing.

View on HN

Also a little clickbaity with "my AI" and then it's all Mistral...

Check out Fast Agent! (I have no affiliation with it, just use it).

https://github.com/evalstate/fast-agent

Techniques like this have been around since GPT-3.5. There are boatloads of papers on the topic.

I have no idea why anyone thinks this is novel. I guess that speaks to the state of HN

Exactly... I thought that implementing STORM was just a basic step in this topic... Looks like we're running in circles.

Mind sharing a link?

Here's a paper on agent architectures including multi agent. A bit old at this point, but a good overview.

https://arxiv.org/abs/2404.11584

Chatgpt shares context between chats. I wonder how that impacts it?

It seems like a good approach though. What you dont want to do is ever suggest that its wrong yourself. Usually it will just assume it is wrong.

Actually what I find impressive is when I do this and it actually pushes back to defend itself.

Does it share context even if no "memory updated" message appears indicating it has stored a fact about you?

I asked ChatGPT and it says no, but then again it's not reliable at introspection or at revealing data about how it works.

I think they are different systems, one is a collection of saved snippets and the other more like RAG over chat history.

ChatGPT assures me it doesn't use RAG (fed from my other chat windows), but will use memory-saved preferences (in the store that can be accessed and reviewed in Settings->Personalization->Memory).

Then again, I don't think ChatGPT is reliable when reporting on its own inner workings.

---

Oh, no, here it says it also references chat history: https://help.openai.com/en/articles/8590148-memory-faq

You can use ChatGPT for these kinds of questions but it needs to use search or research mode, don't ask it in closed book mode.

Reply on news.ycombinator.com