Data science career, AI-powered analytics, and learning-in-public workflows.

Tokens are the currency used by AI models. A token isn't always a single word; it can be multiple segments. Token limitations affect AI speed and context during interactions.

Setting up Hermes Agent is crucial for an optimal experience. Multiple hardware options are available for different budgets. The setup process includes downloading the software and configuring it with models.

AI video technology has significantly advanced. Inky is a lonely octopus featured in a short film. Creating videos can now be done quickly using platforms like OpenArt.

Notebook LM now creates documents, infographics, and multimedia content. Users can explore featured notebooks from renowned sources like The Economist. The AI tool provides business gap analysis for aspiring entrepreneurs. Examples include AI-driven products for health and job market adaptation.

Tina Huang shares her favorite AI tools for various aspects of life. Key tools include Claude Cowork for custom workflows, Claude Chat for general inquiries, and Perplexity for objective searching. In the builder dungeon, AI coding tools like Claude code and Cursor assist in software development.

Explores three efficient OpenClaw setups. Demonstrates methods to enhance productivity. Encourages practical application for immediate results.

Discover three transformative features of Claude Cowork. Learn how these features enhance collaboration and productivity. Get insights on optimizing your workflow with Claude Cowork.

Tina Huang's current AI stack emphasizes fewer tools for deeper use. Claude has become her main tool for thinking and writing. She has canceled several subscriptions by building her own free versions. Cloud code and Warp are her preferred tools for coding. Perplexity is her go-to for search-related tasks.

Co-working can enhance productivity when set up effectively. Five key tools were created: a resource hub, a mission control dashboard, a video asset skill, an investment dashboard, and a daily digest feature. These tools streamline work processes and communications.

Understanding AI agents is key to effective workflow. Push back against AI decisions to ensure accuracy. Learning the fundamentals of AI tools is essential.

AI agents frequently fail due to faulty workflows. Assuming an agent is working can lead to wasted resources. Clean up existing processes before implementing automation.

AI skills are evolving rapidly; an updated roadmap is necessary for 2026. Key foundational skills include investment awareness regarding AI impact, effective prompting, and mastering essential AI tools. Intermediate skills involve understanding and using AI agents to automate tasks and achieve broader goals.

Domain knowledge is crucial for effective AI use. Quality outputs rely on understanding what makes them good. AI should be seen as a skill set, not just a tool. Reduce consumption of AI content; focus on building personal skills.

Tina Huang shares her Claude co-work setup to optimize productivity. The setup includes daily digests, custom dashboards, and automated software building. Key steps involve configuring settings, writing a product requirement document (PRD), and establishing co-work protocols.

The RSTI framework enhances AI prompting. R: Revisit your original prompt with more context. S: Separate prompts into clear, concise sentences. T: Try different phrasings for better outputs. I: Introduce constraints to narrow AI focus.

Use the T.C.R.E.I. framework for effective AI prompting. Provide clear tasks and detailed context. Incorporate references for better output results. Evaluate results and iterate for improvements.

Claude Co-work automates various workflows for personal and business tasks. Users can manage investments, emails, and bookkeeping without coding skills. The software acts as a local AI agent specifically designed for non-technical users.

Open Claw, also known as Claw Bot, is considered dead. Anthropic has introduced a new remote control mode for Claude. Remote control mode and Open Claw are fundamentally different products. Open Claw serves as a local AI agent with diverse capabilities. Remote access tools should not be conflated with Open Claw's functionalities.

Discusses the concept of vibe coding. Explores the implications of emerging technologies. Highlights the complexity of epigenetic engineering.

Choose a single AI chatbot for writing tasks. Use free research tools like NotebookLM. Leverage existing workflow tools with built-in AI features.

White-collar jobs are facing the highest risk of AI disruption. Computer programmers have a 75% task exposure to AI. High-skill, desk-based roles are more affected than physical presence jobs. The most exposed workers tend to be more educated and higher paid. Embracing AI can enhance job performance and opportunities.

Discussion of three specific AI apps created by Tina Huang. A freelancer toolkit to manage contracts, invoices, and payments. An automated presentation builder for preferred slide deck formats. Custom accounting software developed to simplify accounting tasks.

There are four distinct levels of using AI. Most users are found at levels one and two. Level three involves using AI as a thought partner. Level four focuses on building custom systems with AI.

Local AI agents run on your personal machine and autonomously complete tasks. Custom designing local AI agents is crucial for optimal performance. Practical examples include personalized financial tracking and business analysis. Consider hardware specifications and privacy when choosing a machine for local AI agents. This new category of AI products offers significant opportunities for enhanced workflows.

Vibe coding is now called agentic engineering. Thorough planning before building is essential for success. Expect and plan for breakdowns during the development process. Focus on both the method and the product in agentic engineering.
An honest look at how AI fits into a real data science workflow - what helps, what hurts, what's neutral. Strong on: SQL drafting, exploratory data analysis, and writing communications for non-technical stakeholders. Weak on: anything where the data shape isn't obvious from a few rows, or where time leakage is possible. Tina's litmus test for whether to trust an AI-generated analysis before sharing it.