# To Do > [!multi-column] > >> [!bug] Overdue >> ```tasks >> not done >> (due before today) >> hide task count >> hide due date >> hide edit button >> short mode >> ``` > >> [!success] Today >> ```tasks >> not done >> (due on today) >> hide task count >> hide due date >> hide edit button >> short mode >> ``` > [!multi-column] > >> [!note] Current Papers >> ```dataview >> LIST WITHOUT ID file.link >> FROM #paper/current >> SORT file.ctime ASC >> ``` # Health Tracking > [!multi-column] > >> [!abstract] Weight Tracker >> ```tracker >> searchType: frontmatter >> searchTarget: weight >> folder: / >> line: >> title: "Weight Over Time" >> yAxisLabel: Weight (kg) >> lineColor: "#69b3a2" >> ``` > >> [!danger] Beer Tracker >> ```tracker >> searchType: frontmatter >> searchTarget: beer500ml >> folder: / >> line: >> title: "Weekly Beer Pattern (500ml bottles)" >> yAxisLabel: "Bottles" >> lineColor: "#ff6b6b" >> ``` >> >> ```tracker >> searchType: frontmatter >> searchTarget: beer500ml >> folder: / >> summary: >> template: "🍺 Weekly Beer Status:\n- Bottles this week: {{sum()}}/8\n- Remaining: {{8 - sum()}}\n- Standard drink equivalent: {{sum() * 1.52}}\n\n📊 Status: {{8 - sum() >= 0 ? '✅ On track!' : '⚠️ Over budget'}}\n\nℹ️ Quick Reference:\n1 bottle = 1.5 drinks\n2 bottles = 3 drinks\n3 bottles = 4.5 drinks (over limit)\n\n🎯 Session Targets:\n- Ideal: 2 bottles (3 drinks)\n- Max: 3 bottles (4.5 drinks)" >> style: "color:var(--text-normal); background-color: var(--background-secondary); padding: 10px; border-radius: 5px;" >> ``` # Notes > [!multi-column] > >> [!summary]- Created Today >> ```dataview >> LIST WITHOUT ID file.link >> FROM "" >> WHERE file.cday = this.file.day AND file.name != this.file.name >> SORT file.ctime ASC >> ``` > >> [!example]- Modified Today >> ```dataview >> LIST WITHOUT ID file.link >> FROM "" >> WHERE file.mday = this.file.day AND file.name != this.file.name AND file.cday != this.file.day >> SORT file.mtime ASC >> ``` > [!multi-column] > >> [!danger]- Created Yesterday >> ```dataview >> LIST WITHOUT ID file.link >> FROM "" >> WHERE file.cday = date(this.file.day-1) AND file.name != this.file.name >> SORT file.ctime ASC >> ``` > >> [!info]- Created Two Days Ago >> ```dataview >> LIST WITHOUT ID file.link >> FROM "" >> WHERE file.cday = date(this.file.day-2) AND file.name != this.file.name >> SORT file.ctime ASC >> ``` > [!multi-column] > >> [!abstract] Recent Thoughts >> ```dataview >> LIST WITHOUT ID file.link >> FROM #thought >> WHERE date(today) - file.cday <= dur(14 days) >> SORT file.ctime DESC >> ``` ## Quick Links > [!multi-column] > >> [!example] Quick Links >> ```dataview >> LIST WITHOUT ID file.link >> FROM #quicklink >> SORT file.cday DESC >> ``` # [[Scratch Pad]] # Generating Philosophy with LLMs: A Framework Based on Cultivation ## Section 1: The Core Claim ### A. Initial Setup - Philosophers can work with LLMs to generate new philosophical ideas and arguments in ways that parallel how gardeners work with natural systems - The [[gardening analogy]] helps explain how philosophers can work productively with LLMs while acknowledging their patterns and behaviors ### B. Types of Knowledge Required - Working with LLMs requires both technical knowledge of how they function and deep philosophical knowledge - This mirrors Carlson's distinction between [[scientific knowledge]] of nature (geology, biology) and everyday [[practical knowledge]] - The combination enables philosophers to recognize promising paths of inquiry and guide discussion productively ## Section 2: The Brainstorming Objection ### A. The Objection Stated - Using LLMs appears similar to writing down a stream of consciousness to generate philosophical ideas - If this comparison holds, then using LLMs adds nothing new to [[philosophical practice]] - The objection suggests LLMs merely speed up existing thought processes rather than enabling new ones ### B. Why LLM Philosophy Differs from Brainstorming - Brainstorming recombines existing thoughts within one's own conceptual framework - LLM interaction creates a dialogue between the philosopher's knowledge and the system's processed information - The system generates unexpected connections that push beyond typical thought patterns - [[The need]] to communicate clearly with the LLM forces precise articulation of ideas - The LLM's responses highlight hidden assumptions in philosophical thinking ## Section 3: The Midjourney-Garden Framework ### A. Core Elements of Image Generation with Midjourney - Midjourney functions like soil - it provides the environment in which images can grow - The system has its own properties and patterns that determine [[what can]] emerge - These properties both enable and constrain what kinds of images are possible ### B. How Users Work with Midjourney - Prompts function like seeds: * Each prompt introduces specific elements that might grow into images * The quality of [[the prompt]] affects [[what can]] develop * Users must understand what kinds of prompts will be productive * Different prompts create different possibilities for growth - Iteration functions like tending plants: * Users examine what emerges from their prompts * They adjust and refine based on what they see growing * They encourage promising developments through further prompts * They prune away unwanted elements by redirecting the system * Multiple cycles of growth and refinement lead to final images ### C. [[The Role]] of Knowledge - Success [[requires understanding]]: * How the system processes different types of prompts * What kinds of images tend to emerge from different approaches * How to guide development through iteration * When to encourage growth and when to redirect it ## Section 4: Adapting the Framework for Philosophy ### A. The Basic Parallel - LLMs, like Midjourney, provide an environment for growth - Philosophical prompts can plant seeds of ideas - Iteration can develop these ideas further - Knowledge guides [[the process]] ### B. [[The Key Difference]]: Blurred Boundaries - In Midjourney: * Prompts clearly function as seeds * Iteration clearly functions as tending * These roles remain distinct throughout [[the process]] - In philosophical LLM work: * Each prompt both plants ideas and prepares ground for more * Each refinement both develops current ideas and enables new ones * [[The distinction between]] planting and tending breaks down ### C. Examples of the Blurred Boundary - When defining philosophical terms: * The definition itself is a philosophical move * It simultaneously creates conditions for further philosophy * These aren't separate phases but one unified process - When exploring implications: * Each step generates philosophical content * Each step also creates new philosophical possibilities * Growth and preparation happen together - When refining arguments: * Clarification develops existing ideas * Clarification enables new philosophical moves * These functions cannot be separated ### D. Philosophical Significance - This shows how philosophical expertise works differently from image generation: * We can't separate preparing ground from growing ideas * Each move serves multiple functions simultaneously * The process is inherently more integrated * Understanding this helps explain how philosophers can work productively with LLMs while acknowledging their unique properties