Claude Code: Agentic AI code-gen tool

 What's going on with Claude Code? - YouTube @Matthew Berman - YouTube

Introducing Claude Code - YouTube

How I use Claude Code for real engineering - YouTube

Claude Code overview - Claude Code Docs

Claude Code | Claude (web online, in install)

Use Claude Code in VS Code - Claude Code Docs

What's Claude Code? : r/ClaudeAI

Andrej Karpathy on X: "I was inspired by this so I wanted to see if Claude Code can get into my Lutron home automation system. - it found my Lutron controllers on the local wifi network - checked for open ports, connected, got some metadata and identified the devices and their firmware - searched the" / X

NASA: back to the Moon

 Watch CNBC's full interview with NASA Administrator Jared Isaacman - YouTube

Agencywide Town Hall with NASA Administrator Jared Isaacman, Friday, Dec. 19, 2025 - YouTube

NASA Has a New Administrator! Jared Isaacman is FINALLY Confirmed! - YouTube

Jared Isaacman - Wikipedia

Jared Taylor Isaacman (born February 11, 1983) is an American billionaire entrepreneur, pilot, and commercial astronaut who has served as the 15th administrator of NASA since December 2025. He is the founder and chairman of Shift4 Payments, a payment processor, and the founder of Draken International, which provides adversary training to the U.S., British, and other NATO air forces.

Anthropic Claude code examples: artifacts

Use artifacts to visualize and create AI apps, without ever writing a line of code | Claude Help Center

Claude code examples: CodeVerter

Translate code between any programming language

"To translate the code, when a user clicks “Convert Code” it will make a call to Claude to rewrite the code the user entered in the left pane into the coding language selected in the right pane and output the translated code in the right pane."

so the actual translation is done by AI API call, this is just UI

2026: EVs vs EREVs (Extended-Range Electric Vehicles)

Is EREV a new name for "hybrid"?

The concept of using gasoline powered engine to generate electricity, change batteries, 
and drive by using electric motors is not new:
it was used for long time on diesel locomotives / trains,
and recently on Chevy Volt car (discontinued).

While it makes sense to reduce "range anxiety", it is also increasing complexity, cost, and weight.
For small vehicles "pure" EV is more effective, or it soon will be, thanks to battery tech improvements.

Now, with USA energy policy being focused on traditional fuels, and market on large vehicles,
using EREV is better than no using it. Better than nothing. Will it be cost-effective?

Range extender - Wikipedia

Future EVs: Every Electric Vehicle Coming Soon @caranddriver

Over 20 New EVs Are Coming In 2026. These Are The Seven I'm Most Excited About @insideev

Ready Or Not, The EREVs Are Coming. | EV.Guide

2026 Ford F-150 Lightning boasts 700-mile extended range

Hot, New Electric Cars That Are Coming Soon - Consumer Reports

Origin story: Jeep & Land Rover

How One Engineer's 'Mad Idea' Created WW2 Most Reliable Car in Just 49 Days - YouTube

The Jeep That Saved the World | WWII Willys MB Story - YouTube

Origin story/evolution of the Jeep, where did Jeep come from? - YouTube

Jeep - Wikipedia

Why the Ford Jeep is the Greatest Vehicle Ever Made | Jay Leno's Garage - YouTube

How a Broken Jeep Created the Land Rover Legend - YouTube

How Britain Accidentally Built A World Changing Car - The Land Rover - YouTube

AI vs junior developers?

good thinking!

 "AI Can’t Replace Juniors" - AWS CEO - YouTube  @The PrimeTime

The video challenges AI hype regarding the replacement of junior developers, arguing against common industry claims. Here are the key points:

• The speaker critiques overhyped AI predictions about coding, noting that many claims haven't materialized and that software quality is declining (0:00-1:07).
  
  
• AWS CEO Matt Garman believes that replacing junior developers with AI is "one of the dumbest things I've heard," emphasizing their continued value (1:08-1:43).
  
  
• Garman's reasons include junior devs' familiarity with AI tools, their role in avoiding cost-saving mistakes, and their importance in maintaining the talent pipeline (2:30-4:12).
  
  
• The speaker argues that junior developers offer unique value through exploration, emotional investment, and the ability to understand and solve problems beyond explicit instructions, which AI cannot replicate (5:24-7:56).
  
  
• Ultimately, while some companies may attempt to replace junior developers with AI, the video concludes it will be a mistake (8:17-8:22).

Ilya Sutskever: 2026 AI predictions

Ilya Sutskever – We're moving from the age of scaling to the age of research - YouTube

discuss SSI’s strategy, the problems with pre-training, how to improve the generalization of AI models, and how to ensure AGI goes well.

Ilya Sutskever – We're moving from the age of scaling to the age of research

00:00:00 – Explaining model jaggedness 00:09:39 - Emotions and value functions 00:18:49 – What are we scaling? 00:25:13 – Why humans generalize better than models 00:35:45 – Straight-shotting superintelligence 00:46:47 – SSI’s model will learn from deployment 00:55:07 – Alignment 01:18:13 – “We are squarely an age of research company” 01:29:23 -- Self-play and multi-agent 01:32:42 – Research taste

Ilya Sutskever, U of T honorary degree recipient, June 6, 2025 - YouTube

Ilya Sutskever - Wikipedia

Ilya Sutskever FRS (Hebrew: איליה סוצקבר; born 1986) is an Israeli-Canadian computer scientist who specializes in machine learning.[6] He has made several major contributions to the field of deep learning.[7][8][9] With Alex Krizhevsky and Geoffrey Hinton, he co-invented AlexNet, a convolutional neural network.[10] 

Sutskever co-founded and was chief scientist at OpenAI.

EV: Xiaomi SU7: what Apple car could have been?

Driving Xiaomi's Electric Car: Are we Cooked? - YouTube

Living with Xiaomi's Electric Car - It's Insane. - YouTube

Xiaomi SU7 - Wikipedia

AI videos: Cinematic History Tales @YouTube

Excellent "history" videos. Made with the help of AI tools.
Who is making videos like this?
Sure they sound convincing, well produced.
But how much can we trust them?
A "conspiracy" or just clever use of advanced tools?

Cinematic History Tales - YouTube

How Britain Destroyed The World To Stop One Train - YouTube

The Ottoman Empire "Debt Trap": How Britain Bought The Middle East - YouTube

How The U.S. Bankrupted The British Empire - The Secret Bill for WWII - YouTube

Why The Soviet Union Really Collapsed - How Economics Killed the USSR - YouTube

Spain - The Empire That Died of Wealth: How Gold Destroyed Spain - YouTube

and many more...

Now there is even an AI Agent embedded in YouTube,

great for summarizing and asking about videos,
but not for asking meta-questions:

how trust-worthy and correct is the information presented?

I can't help with that. Try asking something else about this video.

It has "guardrails", as expected.
So I asked Google Gemini AI chat directly, essentially an efficient Google search tool

"how historically correct is the information presented in this video (provided transcript)"

And here is the answer... sounds convincing... 

How A Bankrupt Britain Seized Iran's Wealth: - YouTube

The video's depiction of the Anglo-Iranian Oil Company crisis and the 1953 coup is largely historically accurate, though it presents a simplified narrative. Here's a breakdown of the key points and their historical context:

Accurate Representations:

• The Abadan Refinery's Importance: The video correctly portrays the Abadan refinery as the largest in the world at the time and a vital asset to the British economy, which was struggling after World War II.[1]

• Anglo-Iranian Oil Company (AIOC) and British Control: It's true that the AIOC, later BP, was controlled by the British and was a significant source of national pride and revenue. The company's profits far exceeded the royalties paid to Iran, a major point of contention.[1][2]

• Mohammad Mosaddegh and Nationalization: Mosaddegh was a popular nationalist figure who championed the nationalization of Iran's oil industry.[3] The Iranian Parliament did vote to nationalize the AIOC in March 1951.[1] This move was immensely popular in Iran but viewed as a theft by the British.[1]

• British and American Involvement in the Coup: The British, angered by the nationalization, sought to remove Mosaddegh from power.[2] After facing initial resistance from the Truman administration, they found a more receptive audience in President Eisenhower and his administration. The U.S. and Britain then collaborated on a plan to oust Mosaddegh.[2]

• Operation Ajax and CIA/MI6 Roles: The video accurately identifies the coup plot as "Operation Ajax" and highlights the involvement of both the CIA and British intelligence (MI6).[2] The CIA, with British assistance, used bribery, propaganda, and orchestrated riots to undermine Mosaddegh's government.[4]

• The Shah's Role: The Shah was initially hesitant to dismiss the popular Mosaddegh but was eventually persuaded, partly through bribes to his family.[2] After the coup's success, he returned to power and consolidated his rule, leading to a period of dictatorship.[3][4]

• Aftermath and Consequences: The video correctly states that after the coup, U.S. oil companies gained a significant share of Iranian oil, and the U.S. supported the Shah's regime, including the secret police force SAVAK.[3][4] The coup is widely seen as a root cause of Iranian resentment toward the West, contributing to the 1979 revolution.[3]

Points of Simplification or Omission:

• "Operation Boot": The video refers to the initial British plan as "Operation Boot." While there were British plans to oust Mosaddegh, the more commonly known name for the joint US-UK operation is "Operation Ajax."

• Complexity of U.S. Motives: While the video emphasizes the British desire to reclaim their oil monopoly, it simplifies the American motivation. While oil interests were a factor, U.S. policymakers were also heavily influenced by Cold War fears of a potential communist takeover in Iran.[3][5]

• Internal Iranian Politics: The video focuses on the foreign intervention but gives less attention to the complex internal political situation in Iran at the time, including the role of various political factions and social classes.[3]

• Kermit Roosevelt Jr.: While Kermit Roosevelt Jr. was a key figure in the coup, the video's portrayal of him as a lone wolf "American spy" is a simplification. He was leading a well-funded and coordinated operation with numerous agents on the ground.[4]

In conclusion, the video provides a generally accurate and compelling overview of the historical events surrounding the 1953 Iranian coup. However, it simplifies some of the nuances of the situation, particularly regarding American motivations and the intricacies of internal Iranian politics.

Sourceshelp

1. wikipedia.org
2. adst.org
3. explaininghistory.org
4. zinnedproject.org
5. tnsr.org

3D AI: World Labs & book: "The Worlds I See" by Fei-Fei Li, "The Godmother of AI"

 Dr. Fei-Fei Li, The Godmother of AI — Asking Audacious Questions & Finding Your North Star - YouTube  @ Tim Ferriss - YouTube

Dr. Fei-Fei Li is the inaugural Sequoia Professor in the Computer Science Department at Stanford University, a founding co-director of Stanford’s Human-Centered AI Institute, and the co-founder and CEO of World Labs, a generative AI company focusing on Spatial Intelligence. 

She is the author of  book: 

Amazon.com: The Worlds I See: Curiosity, Exploration, and Discovery at the Dawn of AI (Audible Audio Edition): Dr. Fei-Fei Li, Cindy Kay, Macmillan Audio: Books

Fei-Fei Li - Wikipedia

Fei-Fei Li (Chinese: 李飞飞; pinyin: Lǐ Fēifēi; born July 3, 1976)[2] is a Chinese-born American computer scientist[3] known for her pioneering work in artificial intelligence (AI), particularly in computer vision. She is best known for establishing ImageNet, the dataset that enabled rapid advances in computer vision in the 2010s.

World Labs.ai

World Labs is a leading spatial intelligence company, building frontier world models that can perceive, generate, reason, and interact with the 3D world.

AI SDK for TypeScript by Vercel

ai-sdk.dev/docs

AI SDK by Vercel

The AI SDK is the TypeScript toolkit designed to help developers build AI-powered applications and agents with React, Next.js, Vue, Svelte, Node.js, and more.

The AI SDK standardizes integrating artificial intelligence (AI) models across supported providers. This enables developers to focus on building great AI applications, not waste time on technical differences details.

AI SDK Core: generateObject

Generates a typed, structured object for a given prompt and schema using a language model.

It can be used to force the language model to return structured data, e.g. for information extraction, synthetic data generation, or classification tasks.

ai - npm

The AI SDK is a provider-agnostic TypeScript toolkit designed to help you build AI-powered applications and agents using popular UI frameworks like Next.js, React, Svelte, Vue, Angular, and runtimes like Node.js.

To learn more about how to use the AI SDK, check out our API Reference and Documentation.

5M downloads / week

Investing in AI: good info & book

very astute opinion, show experience!

Bill Gurley (@bgurley) is a general partner at Benchmark, a leading venture capital firm in Silicon Valley. His new book

Runnin' Down a Dream: How to Thrive in a Career You Actually Love: Gurley, Bill: 9780593799666: Amazon.com: Books

Life is a use-it-or-lose-it proposition.
Shouldn’t you spend it doing something you love?
This book will teach you how to find your dream job and avoid a career you’ll regret—from a leading venture capitalist, based on his viral college talk.

This title will be released on February 24, 2026.

Legendary Investor Outlines His AI Thesis in 14 Minutes — Bill Gurley - YouTube @Tim Ferris

AI summary:

• AI as a "Real Technology Wave" with Speculation (0:23-1:39): Bill Gurley discusses how every significant technology wave, like AI, inherently attracts speculation and "bubble-like behavior" due to rapid wealth creation. He emphasizes that a real technological shift and speculation often go hand-in-hand.
  
  
• "Circular Deals" in AI Investments (3:06-3:52): Gurley explains "circular deals" where large companies like Microsoft invest in AI startups (e.g., OpenAI), and those startups then agree to purchase services from the investor. He views this as a questionable and non-transparent accounting practice.
  
  
• Concerns for Retail Investors in AI SPVs (4:20-5:28): Gurley expresses concern for retail investors getting involved in AI-related Special Purpose Vehicles (SPVs). He warns that many promoters of these SPVs may not even have the underlying stock, calling it the "wild wild west" and advising extreme caution.
  
  
• Challenges of Private Company Investing (7:10-8:06): The video highlights two main problems with the public investing in private companies: the majority of VC-backed private companies go to zero, and there's a lack of information transparency compared to public markets.
  
  
• Angel Investing Strategy in AI (9:05-9:30): For angel investing in the current AI landscape, Gurley suggests looking for individuals who are highly curious, actively using AI tools, and bring a unique perspective from a specific industry that gives them an advantage.
  
  
• Institutional Investor Focus on AI-Only Deals (9:50-10:41): Currently, institutional investors have "zero interest" in non-AI deals. This means that if an angel-funded deal isn't AI-related, it risks "dying of neglect" as it won't attract future institutional funding.
  
  
• Protecting Your Career with AI (10:43-11:08): Gurley advises everyone, regardless of their field, to start "playing with this stuff" (AI). He believes that being the "most AI-enabled version of yourself" is the best way to protect your career from potential displacement by AI.
  
  
• Investing in "Off the Beaten Path" AI Verticals (12:28-13:05): When investing as an angel, Gurley recommends focusing on "deeper verticals" or niche industries that are not high-priority targets for large AI companies like OpenAI (e.g., waste management). These verticals often involve specific workflows and proprietary datasets that big models won't easily "crush."
  
  
• Importance of Proprietary Data Sets and Workflows (13:16-14:06): Successful AI investments in specific verticals will likely involve proprietary data sets and the ability to build software around existing "workflows"—tasks that need to be automated and integrated with AI, like booking tours in real estate.
  
  
  

Bill Gurley — The AI Era, 10 Days in China, & Life Lessons from Bob Dylan, Jerry Seinfeld,, and More - YouTube   @Tim Ferris

wisdom for career: "don't half-ass it" => rocket fuel for life!

Runnin' Down a Dream: How to Succeed and Thrive in a Career You Love - Bill Gurley 9/14/2018 - YouTube

All-In Summit: Bill Gurley presents 2,851 Miles - YouTube

Legendary Investor Bill Gurley on Investing Rules, Insights from Jeff Bezos, Must-Read Books, & More - YouTube

Bill Gurley, Benchmark Capital (full version) - YouTube

AI dev tool: Google Antigravity

Is this a web "dev help", or "dev replacement" tool?

While based on VS Code, it also includes
full control of Chrome web browser, and "agent manager",
to initiate and manage and test multiple projects and playgrounds in parallel.

The code editor is available, but more like a "fallback" access to check things.
In fact, Antigravity does not "like" sharing control, it does its things its own way.
Very opinionated.

So is it "good", "amazing", or "not for me"?

It is different enough, and provides free access to Google Gemini 3 Pro (unlimited?)

Worth a try for sure.

My take is that this is an evolutionary step in abstraction levels, 
similar to upgrade from assembly/macro (ASM) programming languages
to now common "higher level" languages like C, C++, Python, JavaScript, C# etc.

Since Google is a bit "late to the game", and has a "culture" of attempts for 10x improvements,
it is not a surprise they are "pushing the limits." As they did with Angular 2. And React "won". 

I also think this is a move to a wrong direction.
Non-developers will be lost in advanced tool,
and good developers are not good "managers,"
and good managers are not good developers, no matter abstraction level.

Time will tell... and VS Code will for sure capture some of those ideas,
same as they did with from Cursor. 

Learn the basics of Google Antigravity - YouTube

Google Antigravity: From Beginner to Expert in 14 Minutes - YouTube

Google Antigravity - YouTube

Links

Websiteantigravity.google

Xx.com/antigravity

LinkedInlinkedin.com/showcase/google-antigravity

Agentic AI: Language Model Usage

 Stanford Webinar - Agentic AI: A Progression of Language Model Usage - YouTube.

concept of agentic language models (LMs) and their usage. common limitations of LMs and agentic LM usage patterns, such as reflection, planning, tool usage, and iterative LM usage. Overview of LMs LM Usage and limitations Retrieval Augmented Generation (RAG) Tool usage Agentic LMs Agentic design patterns Insop is a Principal Machine Learning Researcher at GitHub Next. Previously he worked at Microsoft, where he focused on leveraging machine learning and large language models to boost engineering productivity. His projects included fine-tuning open-source large language models with internal code and text, developing document assistance tools, and applying AI to various engineering tasks. He is currently a course developer as well as a course facilitator for Stanford Online’s professional AI program. 00:00 - Introduction 00:10 - Overview of the Talk 01:50 - Training Language Models 02:30 - Modeling Objectives 04:00 - Examples of Training Data Formatting 05:40 - Applications of Language Models 06:50 - Using API for Language Models 09:00 - Best Practices for Prompt Preparation 11:10 - Importance of Clear Instructions 13:40 - Reflection and Improvement Techniques 16:30 - Tool Usage and Function Calling 20:30 - Definition of Agentic Language Models 21:50 - Reasoning and Action in Agentic Models 24:00 - Example of a Customer Support AI Agent 29:20 - Summary of Applications 36:00 - Key Design Patterns in Agentic Models 44:00 - Summary of Agentic Language Model Usage 47:40 - Audience Q&A 50:00 - Addressing Ethical Considerations 54:50 - Getting Started with Language Models 57:00 - Resources for Staying Updated 58:20 - Closing Remarks