Eric_BB

Cool, thanks!

Interesting take. I also think this one can be combined with cutting-edge technologies. For example, the papers ‘Spellburst’, ‘Natural Language is All a Graph Needs’, and ‘Generative Agents: Interactive Simulacra of Human Behavior’ gave me a lot of ideas that can be used in a non-IT domain. In general, I am looking for a way to find more of those easily and quickly.

Interesting, thanks!

More than anything, I’m trying to expose myself to the current technological front because it’s likely that some ideas there haven’t been implemented yet. I totally agree that there are ideas to be found in past situations, and every now and then, an incredible leap forward emerges thanks to some ancient theorem. In fact, I believe it makes sense to combine both approaches. As for the competition of ideas, I don’t see it as much of a problem. Ideas can be combined with others, and even if the exact same idea comes up, there are still numerous fields where it can be implemented

That was funny, thank you

Thank you for the suggestion! I will check out the library and try it without any fine-tuning

Very interesting! Thank you for the idea. I will try to figure out how to do that

This is what I was thinking about using LLM for: 1. As a feature extractor. For example, given the text of misinformation agents, what are the characteristics? C1, C2, C3, etc. Then, do these characteristics appear in these new texts? Assign a label accordingly. 2. I'll give LLM the text on how they usually behave and ask if these new ones are behaving similarly. If so, label them accordingly. (There may also be the possibility to pass graph data in a graph-less way.) 3. Use the extracted information to enhance topology-driven classification

Thanks! Btw, a link to resources would still be appreciated if I need to apply the knowledge to personal projects in the future.

Thank you for your answer. The objective of the assignment is to classify agents of misinformation based on their tweets. An example element of the dataset can be found at this link: https://ibb.co/16VMTCN. There is a dataset for the control group and a dataset of misinformation agents. The idea is to make the model closer to how misinformation agents are via fine-tuning on these datasets. The available HPC resources, including information about GPUs and their quantity, can be viewed at this link: https://www.carc.usc.edu/user-information/user-guides/hpc-ba...

Fascinating

Thanks!

Congratulations on the launch! Your app made me excited, although I don't believe I am the target audience. I am a graduate student, I have experience with Python and have built some simple websites using Django, Alpine, HTMX, and Tailwind. I have a few days off and would like to build some projects quickly. Does anyone have any recommendations, ideas, guides, or examples on how I can leverage ChatGPT to build quickly using a strategy similar to the one used by the OP?