That's not actually research though. The LLM API is only requesting a few of the top search results from a search engine and then adding those web pages to its context window.
That might work for simple tasks, but it's easily susceptible to prompt injection attacks and there's no way to validate the quality if it's statistically novel enough and outside of the core training data.
That might work for simple tasks, but it's easily susceptible to prompt injection attacks and there's no way to validate the quality if it's statistically novel enough and outside of the core training data.