[ajdecon]

> The idea of the dashboard is the following: I run the Codex through a web chat to identify the relevant quotes — relevant for my dissertation topic — and how they are relevant, it combines them into a number of claims connected with each quote with a link. And then I review each quote and each claim manually and tick the boxes.

I’d be most concerned about this component of your process, tbh. IIUC, you’re not just using the LLM to identify relevant papers, i.e. a fancy search engine. You’re also extracting specific statements, divorced from their context in a given paper, and using these to make claims for your research.

Even if you validate that the quotes are actually present in the papers, are you also reading the full papers to ensure you understand the overall results of the paper and what the quotes mean in that context? Or are you just identifying hopefully-relevant snippets and combining them?

[latand6]

good catch, yeah, I'm basically having a conversation with codex about each paper where it explains me the paper and answers my questions. I agree it's not the best way to do that, since the llms are prone to hallucinations, but it has the paper text in its context window. Also I find it very useful that gpt5.4 model tends to question and critique my claims I ask it to note down