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",

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.