undefined | Better HN

0 pointsgenerallyjosh1mo ago0 comments

One of the first skills I made for Claude was a research skill.

I give it a question (narrow or really broad), and the model does a bunch of web searches using subagents, to try and get a comprehensive answer using current results

The important part is, when the model answers, I have it cite its sources, using direct links. So, I can directly confirm the accuracy and quality of any info it finds

It's been super helpful. I can give it super broad questions like "Here's the architecture and environment details I'm planning for a new project. Can you see if there's any known issues with this setup". Then, it'll give me direct links + summaries to any relevant pages.

Saves a ton of time manually searching through the haystack, and so far, the latest models are pretty good about not missing important things (and catching plenty of things I missed)

0 comments

nosuchthing1mo ago

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.

j / k navigate · click thread line to collapse