User Tools

Site Tools


tutorials:ai_llm_tools

Differences

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

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision
Previous revision
tutorials:ai_llm_tools [2025/07/24 10:59] – [What are LLMs?] chkuotutorials:ai_llm_tools [2026/02/09 10:54] (current) chkuo
Line 40: Line 40:
     * Particularly helpful in the context of emotional support     * Particularly helpful in the context of emotional support
   * In some ways, LLMs are like crystals of human knowledge   * In some ways, LLMs are like crystals of human knowledge
-  * Useful for learning new topics efficiently through interactive Q&A +    * Useful for learning new topics efficiently through interactive Q&A 
-  * Perform especially well on topics with abundant, high-quality training data+    * Perform especially well on topics with abundant, high-quality training data
   * Highly proficient in language, particularly useful for clear and precise expression of ideas   * Highly proficient in language, particularly useful for clear and precise expression of ideas
   * Great tools for self-improvement   * Great tools for self-improvement
Line 88: Line 88:
     * Trained to be agreeable, they often conform to both your explicit instructions and implicit tone     * Trained to be agreeable, they often conform to both your explicit instructions and implicit tone
     * Helpful to make your implicit thoughts become explicit and better organized     * Helpful to make your implicit thoughts become explicit and better organized
-  * Suggested practice 
-    * Start with a solid frame of reference 
-      * Provide clear context for the task, including your goals and expectations 
-      * What exactly do you want to obtain? 
-      * How do you want the LLM to act? 
-      * Are your expectations realistic? 
-      * Examples of possible uses (varying in feasibility and reliability): 
-        * Polish arguments 
-        * Organize thoughts 
-        * Brainstorm new ideas 
-        * Identify major gaps in reasoning 
-        * Provide critical review 
-    * Assess the output, make decisions, and provide feedback 
-    * Use an iterative process; may involve gradual refinement or drastic changes 
-    * Fact check, fact check, and fact check!!! 
-    * Know when to stop; did the last iteration provide meaningful improvement? 
  
 +===== Suggested practice =====
 +  * Start with a solid frame of reference
 +    * Provide clear context for the task, including your goals and expectations
 +      * Learn the basic of markdown can be very helpful ("help me to learn the very basic of markdown language in 5 minutes, explain to me how can I use this in my prompt to improve the clarity of my instruction to you")
 +    * What exactly do you want to obtain?
 +    * How do you want the LLM to act?
 +    * Are your expectations realistic?
 +    * Examples of possible uses (varying in feasibility and reliability):
 +      * Polish arguments
 +      * Organize thoughts
 +      * Brainstorm new ideas
 +      * Identify major gaps in reasoning
 +      * Provide critical review
 +  * Assess the output, make decisions, and provide feedback
 +  * Use an iterative process; may involve gradual refinement or drastic changes
 +  * Fact check, fact check, and fact check!!!
 +  * Know when to stop; did the last iteration provide meaningful improvement?
 +  * Exercises
 +    * Use figure legends as input, ask for a manuscript outline as output; explore different ways of ordering the figures
 +    * Use a poster abstract as input, ask for possible titles as output; compare how each emphasizes different aspects of the work or addresses different audiences
  
 ===== Human–AI Dynamics ===== ===== Human–AI Dynamics =====
Line 119: Line 123:
  
 ===== Use Cases ===== ===== 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   * 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   * 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   * 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
  
  
-===== Additional Points =====+===== Practical Advice & Next Steps =====
   * Test the tool with topics that you know well first for evaluation   * Test the tool with topics that you know well first for evaluation
   * Push boundaries, learn the situations that LLMs are useful (or not)   * Push boundaries, learn the situations that LLMs are useful (or not)
tutorials/ai_llm_tools.1753325991.txt.gz · Last modified: by chkuo