![]() But the amount of computation is still a lot more than querying indexes. Granted, the size of the neural network is not comparable to search engine databases. LLMs, on the other hand, run information through the entire neural network every time they receive a prompt. Therefore, even though the body of online information is growing, search engine speed is not dropping. They have indexing, sorting, and search algorithms that can pinpoint the right records at very fast speeds. Search engines don’t need to browse their entire dataset for each query. LLMs such as ChatGPT take several seconds to compose their responses. Companies like Google have created highly optimized database infrastructure that can find millions of answers in less than a second. LLMs also have an inference speed problem. Again, we see the traces of search engine components. ![]() The operators of the LLM search engine also need mechanisms and tools to determine which web sources are reliable sources of knowledge and should be given priority. Setting up and parallelizing these processors for training and running the models is both a technical and financial challenge. ![]() Since there is no single piece of hardware that can fit the model, it has to be broken up and spread across several processors, such as A100 GPUs. And it has to be done multiple times per day if it is to stay up to date with the latest news.īased on GPT 3.5, ChatGPT probably has at least 175 billion parameters. Maybe not every update will require full retraining, but it will nonetheless be much more expensive than adding and modifying records in a search engine database. Updating the search engine database is also a very cost-effective operation.īut for large language models, adding new knowledge requires retraining the model. Search engines have the tools and software to constantly index new and modified pages. Another challenge ChatGPT and other LLMs face is updating their knowledge base. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |