The vendor changed the control parameters for the Chatbot ( https://lenr-canr.org/wordpress/?page_id=2988). When you ask a question, it now takes longer to respond. I think it often takes about 30 seconds. It is worth the delay, because it is improved in various ways. It does a deeper search. I think the answers are more accurate. It remembers context better, from one query to another. You do not have to keep repeating the subject, or the name of the paper. It does a better job finding a URL (where that is available), or quoting a section of the paper verbatim. A verbatim quote is handy because you can use it in a Google search to locate the paper it comes from.
Here is an example, for the Index Bot (the one on top). BOT: Hello! What can I do for you today? ME: Has E. Storms written a paper about how to construct a calorimeter? BOT: Yes, E. Storms has written a paper titled "How to Make A Cheap and Effective Seebeck Calorimeter" which describes how to construct a Seebeck calorimeter that is effective in measuring heat generation over a wide range of power with high sensitivity and stability. The paper also provides a successful example of constructing such a device, although it requires considerable investment of time. The paper was presented at the Tenth International Conference on Cold Fusion in 2003 and can be found on the LENR-CANR.org website. ME: What is the URL of this paper? [With the previous settings, the Bot would have asked, "what paper?" It lost track.] BOT: The URL for the paper "How to Make A Cheap and Effective Seebeck Calorimeter" by E. Storms is http://lenr-canr.org/acrobat/StormsEhowtomakea.pdf. ME: What does the abstract say? Quote it verbatim. BOT: "The Seebeck calorimeter is very effective in measuring heat generation over a wide range of power and with high sensitivity and stability. Such a device can be constructed cheaply and easily, although with considerable investment of time. A successful example is described." Note: If you don't say "quote it verbatim" a Chatbot is apt to summarize the abstract instead. I have replaced some of the files with new versions in text format, derived from the Amazon AWS Textract OCR program. They work better than the previous version. I will replace all of the files in the coming days. If you want to test the new files and the new, slower but better performance, ask any question from any issue of the JCMNS. JCMNS issues are here: https://lenr-canr.org/wordpress/?page_id=1495
