Can the presence of a URL in an LLM prompt influence the output based on the content of that URL?
I think, yes! But it took me weeks of experimentation and I learnt a lot about what User Agents do and what data is in the models
There's a very clear optimism within the developer ecosystem in China (and also India) that I would love to see more back home and in the US.
It's interesting that there's a similar set of challenges that people face, especially around LLMs and their use.
I've worked with a good number of lecturers and the staff here. Would thoroughly recommend them if you are thinking about a CompSci course (it's the future)