More notes, and set time zone to Europe.

For the Kagi search, the 30B-A3B model kept answering in chinese. I see there was an update of this model yesterday, not sure I have the latest version.

agentic_search.py

@@ -24,7 +24,7 @@ tools = [
     {'mcpServers': {  # You can specify the MCP configuration file
         'time': {
             'command': 'uvx',
-            'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
+            'args': ['mcp-server-time', '--local-timezone=Europe/London']
         },
         "fetch": {
             "command": "uvx",
@@ -45,12 +45,9 @@ bot = Assistant(llm=llm_cfg, function_list=tools)
 # Streaming generation
 messages = [{'role': 'user',
              'content':
-                 """" - It is important that you provide hyperlinks to all search results, otherwise we get a penalty of 20 dollars.
-                      - Research: "Search about Domain Driven Design between published in the last 5 years."
-     - **Analysis**: "Summarize the key findings of these studies and identify 3 common benefits. Provide references"
-     - **Synthesis**: "Create a blog post outlining these concerns and potential solutions, include the references."
-
-              """}]
+                 """"- ***Research** What is enshittification, and who came up with it?
+                 -- **Analyze** Developments around enshittification in the last five years, and related concepts.
+                 -- **Answer** What is enshittification, and what does it mean for society?"""}]
 
 final_responses = None
 # Consider adding error handling around bot.run

notes/ddd-studies.md

@@ -1,6 +1,19 @@
+DDD Studies search, with and without links
+=====
+
+I initially failed to get urls in the result. I then added a 20 dollar penalty, that did seem to encourage the LLM. I had read about this style of prompting, but not needed it yet...
+
+Below are the two results, one without and one with 20 dollar penalty.
 
 # [Without 20 dollar penalty](https://example.com/no-penalty)
 
+Prompt
+----
+
+- **Research**: "Search about Domain Driven Design between published in the last 5 years."
+- **Analysis**: "Summarize the key findings of these studies and identify 3 common benefits. Provide references"
+- **Synthesis**: "Create a blog post outlining these concerns and potential solutions, include the references."
+
 ### **1. Core Focus of DDD in Microservices**
 - **Alignment of Business and Technical Concerns**: DDD is emphasized as a methodology to bridge the gap between business requirements and technical implementation by fostering a deep understanding of the business domain (e.g., "Domain-Driven Design (DDD) has emerged as a powerful methodology...").
 - **Microservices Architecture (MSA)**: DDD is critical for addressing the challenges of defining microservice boundaries, as noted in studies like *"Domain-Driven Design for Microservices: An Evidence-Based Investigation"* (2024), which highlights its role in iterative domain modeling using patterns and practices.

notes/enshittification.md

@@ -0,0 +1,58 @@
+Enshittification, origin and meaning - example prompt and response
+====================================
+
+I had a chat with Mark Dalgarno, he asked me if I knew the term Enshittification. I do, but I got the author wrong. I decided to ask some local llms, and they were mostly funny, but not accurate about the source, and also not always the meaning.  Llama3.1 was honest, and said it did not know.
+
+So I fed it into the agentic search using a similar prompt as the ddd studies
+
+Prompt
+=====
+
+***Research** What is enshittification, and who came up with it?
+**Analyze** Developments around enshittification in the last five years, and related concepts.
+**Answer** What is enshittification, and what does it mean for society?
+
+
+Processing
+=====
+It performed at least three searches on Duck Duck Go, and it got rate limited for the first time.
+The script I use to interface with DDG tries to behave itself. See [pyproject.toml](pyproject.toml) for source.
+
+'it' was hf.co/unsloth/Qwen3-30B-A3B-GGUF:Q5_K_M 
+
+Search queries generated
+-----
+
+All with a `count` of 5 (5 results?) and SafeSearch 'moderate'.
+
+- **origin of enshittification term**
+- **enshittification developments last 5 years**
+
+This query got rate limited. It is interesting to see in the 'think' section below that the LLM noticed 
+the errors and dealt with it. It tried **related concepts to enshittification** and that failed as well.
+
+Thinking tokens
+-----
+
+The interesting bit is at the bottom "Since the tool calls are causing issues, it's better to use the existing data to formulate the response."
+
+> Okay, the user is asking about the origin of the term "enshittification." Let me check the tools available. There's the ddg-search-duckduckgo_web_search function, but the previous attempt resulted in errors like "DDG detected an anomaly" and "Rate limit exceeded." Hmm, maybe the user tried to fetch too many results or there's a limit on the number of searches. Since the initial search didn't work, perhaps I should try a different approach. Wait, the user provided some search results from Wikipedia, etymonline, Merriam-Webster, Wiktionary, and Know Your Meme. Maybe I can use that information directly instead of calling the function again. The user might not need the tool call if the answer is already in the provided results. Let me summarize the origin based on those sources. The term was coined by Cory Doctorow in 2022, meaning the deliberate worsening of services for profit. The Wikipedia entry mentions it's also called platform decay. Etymonline says it's from "enshittify" meaning to make worse. Merriam-Webster explains the structure of the word. So, combining these points, the answer should cover the origin, definition, and examples from the sources provided. Since the tool calls are causing issues, it's better to use the existing data to formulate the response.
+
+Response
+=======
+
+The term **"enshittification"** was coined in 2022 by Canadian-English tech writer **Cory Doctorow**. It describes the process by which online platforms or services deliberately degrade in quality over time, often to prioritize profit over user experience. Here's a breakdown of its origin and meaning based on the sources:
+
+1. **Coined by Cory Doctorow**:  
+   - The term originated as a satirical take on "crapification" or "platform decay," reflecting how companies shift focus from users to shareholders, leading to worse services (e.g., invasive data collection, ad overload, reduced functionality).
+
+2. **Etymology**:  
+   - Combines the prefix **"en-"** (meaning "to cause to be") with **"shittier"** (a vulgar slang term for worse) and the suffix **"-ification"** (denoting a process of making). It literally translates to "making something shittier."
+
+3. **Definition**:  
+   - A deliberate strategy by companies to degrade their offerings over time, often to maximize profits. For example, Twitter's evolution under Elon Musk was cited as an example of "enshittification" in some sources.
+
+4. **Popularization**:  
+   - While Doctorow popularized the term, it has since been adopted in discussions about tech ethics, corporate accountability, and the decline of user-centric platforms.
+
+For more context, you can explore the [Wikipedia entry](https://en.wikipedia.org/wiki/Enshittification) or [etymonline](https://www.etymonline.com/word/enshittification). Let me know if you'd like further details!

notes/kagi.md

@@ -0,0 +1,55 @@
+Prompt
+=====
+***Research** Kagi search, privacy and company investors and financials.
+**Analyze** Recent developments around Kagi
+**Answer** Is it a company that I can trust with my money and data?
+
+
+Process
+======
+
+Both the 30B-A3B and 32B qenerated only one query, and asked for 10 results.
+See [the enshittification search] (enshittification.md)) for comparison, where multiple queries of 5 results were asked for.
+
+It seemed to have found and picked mostly pages from the company. 
+It neither has [Daring Fireball's recommendation](https://daringfireball.net/2025/04/try_switching_to_kagi), nor a critique.
+
+Result
+======
+
+Kagi Search appears to prioritize user privacy through a combination of business model design, technical features, and transparent data practices. Here's a structured overview of how Kagi handles privacy, supported by the provided information:
+
+### **1. Business Model & Financial Incentives**
+- **Subscription-Based Revenue**: Kagi operates on a paid subscription model, earning revenue only when users pay for its services. This eliminates financial incentives tied to data monetization or advertising, reducing the likelihood of compromising privacy to attract advertisers.
+- **No User Data Monetization**: The service explicitly states it does not collect, sell, or monetize user data, aligning with their mission to avoid trading user privacy for profit.
+
+### **2. Data Collection & Retention Policies**
+- **Minimal Data Collection**: Kagi claims to collect no user information beyond what is necessary for basic functionality. This aligns with their privacy policy, which emphasizes refraining from tracking or storing user data.
+- **No Training on User Data**: When using third-party AI models, Kagi prioritizes services that do not retain user data or use it for training. This ensures user queries and interactions are not stored or analyzed for model improvements.
+
+### **3. Privacy-Enhancing Features**
+- **Privacy Pass Authentication**: A key feature allows users to access Kagi Search without revealing their identity, akin to Tor-like anonymity. This enables private searches without tracking or requiring account creation.
+- **Non-Identifiable Indexes**: Results are augmented using non-commercial indexes, which may reduce reliance on user-specific data for personalization, further protecting anonymity.
+
+### **4. Transparency & Documentation**
+- **Public Privacy Policy**: Kagi provides detailed documentation (e.g., [Privacy Policy](https://kagi.com/privacy)) outlining their commitment to privacy, including how data is handled, third-party services used, and their stance on law enforcement requests.
+- **Comparison with Competitors**: Their documentation includes comparisons with other search engines and AI providers, highlighting their strict privacy practices versus those that monetize user data.
+
+### **5. Technical Practices**
+- **Privacy-Respecting Third-Party Tools**: Kagi uses services that prioritize user privacy, ensuring no data retention or misuse by external entities.
+- **No Personalized Tracking**: Their search results are powered by non-commercial indexes, minimizing the use of user data for personalization or behavioral analysis.
+
+### **6. Legal Compliance & Limitations**
+- **No Explicit Reference to Law Enforcement Access**: While the privacy policy does not address law enforcement data requests, their business model and documentation suggest a strong stance against unnecessary data sharing. However, compliance with legal mandates (e.g., court orders) may still occur, though this is not confirmed in the provided sources.
+- **Anonymous Access Options**: Features like Privacy Pass and Tor compatibility allow users to bypass traditional authentication, enhancing privacy in scenarios where anonymity is critical.
+
+### **7. User Trust & Reputation**
+- **Transparent Documentation**: Kagi openly communicates their data practices, fostering user trust. For example, their [LLM Privacy Page](https://help.kagi.com/docs/llm-privacy) clarifies that their AI models do not train on user data.
+- **Positive Community Mentions**: References in sources (e.g., [LLM Privacy](https://help.kagi.com/docs/llm-privacy)) suggest users and third parties acknowledge their privacy-first approach.
+
+### **Key Takeaways**
+- **Strengths**: Minimal data collection, subscription-based model, Privacy Pass feature, and transparent documentation.
+- **Potential Limitations**: Ambiguity around law enforcement access and reliance on third-party services may require further clarification.
+- **Comparison to Others**: Kagi differentiates itself from ad-based search engines (e.g., Google) by prioritizing privacy without compromising functionality.
+
+In summary, Kagi Search is designed to protect user privacy through a combination of business model transparency, technical anonymity features, and strict data-minimization practices, making it a strong choice for users prioritizing confidentiality in their online activities.