Differences

This shows you the differences between two versions of the page.

--- tutorials:ai_llm_tools [2025/06/12 17:40] – [Value] chkuo
+++ tutorials:ai_llm_tools [2025/07/24 17:23] (current) – [Use Cases] chkuo
@@ Line 20: / Line 20: @@
 ==== What are LLMs? ====
-  * Artificial intelligence systems trained on large collections of text to generate human-like responses
-    * Predict the next word (token) based on statistical patterns
-    * Do not “think” or “understand” like humans
-    * Mimic intelligence, but are not truly “intelligent”; can be very convincing!
   * Key concept
     * LLMs work by estimating probability relationships among tokens, not by indexing content like a database such as Wikipedia
   * Key terms
-    * Token: basic unit for LLMs to process information
+    * Token: the basic unit of text that LLMs process; typically equivalent to or smaller than a word
     * Prompt: user input
     * Session: a series of user input and LLM output
       * Good practice: limit the scope and length of individual sessions
     * Memory: information kept from previous interactions; some systems provide this function
+  * Artificial intelligence systems trained on large collections of text to generate human-like responses
+    * Human: form thoughts first, then use language to communicate those thoughts
+    * LLM: generate language by predict the next word (token) based on statistical patterns
+    * LLMs do not “think” or “understand” like humans do; the appearance of “thought” is a byproduct of those patterns
+    * LLMs mimic intelligence, but are not truly “intelligent”; can be very convincing!
@@ Line 118: / Line 119: @@
 ===== Use Cases =====
-  * Writing and obtaining feedback as a way of thinking; force LLMs to criticize and challenge your thoughts
+  * Force LLMs to criticize and challenge your thoughts
   * Use the "Deep Research" function (available in both ChatGPT & Gemini) for targeted search of PubMed and follow-up summary
-  * Reading dense papers
+  * Help to read dense papers
   * Build custom databases of selected references using NotebookLM by Google
-  * Grammar check and copy editing
+  * Perform grammar check and copy editing
   * Prepare for discussion with seminar speakers; info about you and the speaker as the input, suggestions of questions to ask as the output
-  * Drafting or refining emails (with tone sensitivity)
+  * Draft or refine emails (with tone sensitivity)
-  * Technology related, such as server/intranet setup, hardware purchase planning, Linux/NAS configuration, or organization of computer files and directories
+  * Obtain technology-related suggestions, such as server/intranet setup, hardware purchase planning, Linux/NAS configuration, or organization of computer files and directories