Sensitive content

This media may contain sensitive content.

Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Week-long stroking challenge ... How often should I watch this vid on loop till Jul-26? 😵‍💫 Likes/Reposts add +1x/+2x each! 🥵 #pussyfree #fistfucker #loser #submission #humiliation #pumpslut #pornChallenge

pornagotchi's profile picture

🎀pornagotchi🎀

81,827 subscribers

63,849 görüntüleme • 2 ay önce •via X (Twitter)

NSFW#pussyfree#fistfucker#loser#submission#humiliation#pumpslut#pornChallenge
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

-> If you’re looking for a job -> right now, there are three -> Claude certifications that -> you should do this week -> and then put them on your -> LinkedIn, they are all -> completely free, and they -> come from Anthropic, -> which is the company -> that's behind Claude. -> And jobs that need AI skills -> pay 56% more than jobs -> that don’t, So, I think -> spending a few hours this -> week to knock out these -> three courses and then -> add them to your LinkedIn -> will really go a long way -> The first one is called -> Claude 101, and this -> essentially just goes over -> what Claude is and when -> you should use chat versus -> co-work versus code, how -> projects and skills work, -> and how to connect all -> of your tools and apps -> like Gmail, Notion, Slack, -> and other tools that you use -> And the second course -> is called AI Fluency -> Framework and Foundations -> Inside this one, there are -> 13 lessons on how to -> actually work with AI. -> It goes over things like -> effective prompting, critical -> thinking on the outputs, -> and it has a vocabulary -> sheet that you’ll want -> to read and save for later. -> And the third one is -> Intro to Claude Cowork -> Claude Cowork is where -> you can actually get stuff -> done with Claude. -> So, this course covers -> projects, skills, plug-ins, -> scheduling tasks, handling -> files, and then also how -> to pick the right model -> for the job, and then when -> you finish these courses, -> just go to your LinkedIn -> and go to your profile -> Click "Add section," and -> then go to "Licenses -> and certifications" and -> add all three of these. -> And then when you land -> the interview, you should -> talk about your AI fluency -> often as you possibly can -> I feel pretty confident that -> you’ll truly be able to -> differentiate yourself -> from other candidates -> if you do this
1:21

-> If you’re looking for a job -> right now, there are three -> Claude certifications that -> you should do this week -> and then put them on your -> LinkedIn, they are all -> completely free, and they -> come from Anthropic, -> which is the company -> that's behind Claude. -> And jobs that need AI skills -> pay 56% more than jobs -> that don’t, So, I think -> spending a few hours this -> week to knock out these -> three courses and then -> add them to your LinkedIn -> will really go a long way -> The first one is called -> Claude 101, and this -> essentially just goes over -> what Claude is and when -> you should use chat versus -> co-work versus code, how -> projects and skills work, -> and how to connect all -> of your tools and apps -> like Gmail, Notion, Slack, -> and other tools that you use -> And the second course -> is called AI Fluency -> Framework and Foundations -> Inside this one, there are -> 13 lessons on how to -> actually work with AI. -> It goes over things like -> effective prompting, critical -> thinking on the outputs, -> and it has a vocabulary -> sheet that you’ll want -> to read and save for later. -> And the third one is -> Intro to Claude Cowork -> Claude Cowork is where -> you can actually get stuff -> done with Claude. -> So, this course covers -> projects, skills, plug-ins, -> scheduling tasks, handling -> files, and then also how -> to pick the right model -> for the job, and then when -> you finish these courses, -> just go to your LinkedIn -> and go to your profile -> Click "Add section," and -> then go to "Licenses -> and certifications" and -> add all three of these. -> And then when you land -> the interview, you should -> talk about your AI fluency -> often as you possibly can -> I feel pretty confident that -> you’ll truly be able to -> differentiate yourself -> from other candidates -> if you do this

BeingInvested

13,130 görüntüleme • 3 ay önce

Really enjoyed chatting with Michael Nielsen about how we recognize scientific progress. It's especially relevant for closing the RL verification loop for scientific discovery. But it's also a surprisingly mysterious and elusive question when you look at the history of human science. We approach this question stories like Einstein (who claimed that he hadn't even heard of the famous Michelson-Morley experiment, which is supposed to have motivated special relativity, until after he had come up with the theory), Darwin (why did it take till 1859 to lay out an idea whose essence every farmer since antiquity must have observed?), Prout (how do you recognize that isotopes exist if you cannot chemically separate them?), and many others. The verification loop on scientific ideas is often extremely long and weirdly hostile. Ancient Athenians dismissed Aristarchus's heliocentrism in the 3rd century BC because it would imply that the stars should shift in the sky as the Earth orbits the sun. The first successful measurement of stellar parallax was in 1838. That's a 2,000-year verification loop. But clearly human science is able to make progress faster than raw experimental falsification/verification would imply, and in cases where experiments are very ambiguous. How? Michael has some very deep and provocative hypotheses about the nature of progress. One I found especially thought-provoking is that aliens will likely have a VERY different science + tech stack than us. Which contradicts the common sense picture of a linear tech tree that I was assuming. And has some interesting implications about how future civilizations might trade and cooperate with each other. So many other interesting ideas. Hope you enjoy this as much as I did. 0:00:00 – How scientific progress outpaces its verification loops 0:17:51 – Newton was the last of the magicians 0:23:26 – Why wasn’t natural selection obvious much earlier? 0:29:52 – Could gradient descent have discovered general relativity? 0:50:54 – Why aliens will have a different tech stack than us 1:15:26 – Are there infinitely many deep scientific principles left to discover? 1:26:25 – What drew Michael to quantum computing so early? 1:35:29 – Does science need a new way to assign credit? 1:43:57 – Prolificness versus depth 1:49:17 – What it takes to actually internalize what you learn Look up Dwarkesh Podcast on YouTube, Apple Podcasts, or Spotify.
2:03:03

Really enjoyed chatting with Michael Nielsen about how we recognize scientific progress. It's especially relevant for closing the RL verification loop for scientific discovery. But it's also a surprisingly mysterious and elusive question when you look at the history of human science. We approach this question stories like Einstein (who claimed that he hadn't even heard of the famous Michelson-Morley experiment, which is supposed to have motivated special relativity, until after he had come up with the theory), Darwin (why did it take till 1859 to lay out an idea whose essence every farmer since antiquity must have observed?), Prout (how do you recognize that isotopes exist if you cannot chemically separate them?), and many others. The verification loop on scientific ideas is often extremely long and weirdly hostile. Ancient Athenians dismissed Aristarchus's heliocentrism in the 3rd century BC because it would imply that the stars should shift in the sky as the Earth orbits the sun. The first successful measurement of stellar parallax was in 1838. That's a 2,000-year verification loop. But clearly human science is able to make progress faster than raw experimental falsification/verification would imply, and in cases where experiments are very ambiguous. How? Michael has some very deep and provocative hypotheses about the nature of progress. One I found especially thought-provoking is that aliens will likely have a VERY different science + tech stack than us. Which contradicts the common sense picture of a linear tech tree that I was assuming. And has some interesting implications about how future civilizations might trade and cooperate with each other. So many other interesting ideas. Hope you enjoy this as much as I did. 0:00:00 – How scientific progress outpaces its verification loops 0:17:51 – Newton was the last of the magicians 0:23:26 – Why wasn’t natural selection obvious much earlier? 0:29:52 – Could gradient descent have discovered general relativity? 0:50:54 – Why aliens will have a different tech stack than us 1:15:26 – Are there infinitely many deep scientific principles left to discover? 1:26:25 – What drew Michael to quantum computing so early? 1:35:29 – Does science need a new way to assign credit? 1:43:57 – Prolificness versus depth 1:49:17 – What it takes to actually internalize what you learn Look up Dwarkesh Podcast on YouTube, Apple Podcasts, or Spotify.

Dwarkesh Patel

291,902 görüntüleme • 5 ay önce

Xavier Leroy (creator of OCaml) is an expert in compilers, formal verification of software and functional programming. This interview should be an approachable resource if you're curious about formal verification of software since I was learning that on the fly during it. In this episode: • OCaml compared with Rust and JavaScript • What is formal verification and how does it work • How languages call each other across boundaries • How to address "almost-correct" LLM code • How type inference works in programming languages Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsor of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at Chapters: 00:00 - Intro 00:43 - What sets OCaml apart 04:39 - OCaml vs Rust 07:57 - Why is manual memory management more performant 11:21 - Javascript vs OCaml 14:00 - Famous Rob Pike quote 16:05 - Type inference and how it works 22:12 - What is formal verification and how does it work 40:07 - What made multicore support difficult for OCaml 50:17 - How programming languages interface and call each other 57:41 - The danger of almost-correct LLM code 01:05:39 - How LLMs will change programming languages 01:10:26 - Industry vs academia 01:15:05 - Most interesting unsolved problems 01:18:30 - Top book recommendations for engineers 01:21:17 - Advice for his younger self 01:23:31 - Outro
1:24:27

Xavier Leroy (creator of OCaml) is an expert in compilers, formal verification of software and functional programming. This interview should be an approachable resource if you're curious about formal verification of software since I was learning that on the fly during it. In this episode: • OCaml compared with Rust and JavaScript • What is formal verification and how does it work • How languages call each other across boundaries • How to address "almost-correct" LLM code • How type inference works in programming languages Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsor of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at Chapters: 00:00 - Intro 00:43 - What sets OCaml apart 04:39 - OCaml vs Rust 07:57 - Why is manual memory management more performant 11:21 - Javascript vs OCaml 14:00 - Famous Rob Pike quote 16:05 - Type inference and how it works 22:12 - What is formal verification and how does it work 40:07 - What made multicore support difficult for OCaml 50:17 - How programming languages interface and call each other 57:41 - The danger of almost-correct LLM code 01:05:39 - How LLMs will change programming languages 01:10:26 - Industry vs academia 01:15:05 - Most interesting unsolved problems 01:18:30 - Top book recommendations for engineers 01:21:17 - Advice for his younger self 01:23:31 - Outro

Ryan Peterman

23,942 görüntüleme • 2 ay önce

Claude Code can ship a 45-second animated explainer ad in 30 minutes. No video editor needed, just CC + skills. Here's how I made this video for Soteri Skin 👇 1. /plan Concept Brief (Claude Code) I handwrite a concept brief, then chat with the agent to iterate on it. The agent gathers any raw materials we might need - context about the brand, product images, end card, etc. The concept brief details the concept, characters, visual style, script, etc 2. /prepare a moodboard (CC + GPT Image 2 + ElevenLabs) After reviewing the script, generate: - character reference images - voiceover samples for the characters / narrator - the storyboard (scene by scene grid) - a few keyframe scenes 3. /generate Keyframes for each scene (CC uses Nano Banana or GPT Image 2) Uses the character references from the previous step to generate keyframes for each scene. I probably should have done a round of iteration at this step – there's some character drift and the pH meter representation could have been better. 4. /animate Keyframe → Animated Clip (CC uses Fal Seedance) Generate 2-4 representative scenes first to see a preview. If it looks good, then generate everything. 5. /stitch (CC + ffmpeg + ElevenLabs) - Stitch clips together with hard cut - Add a music score + SFX - Sync clips to the VO - Add captions - Review and edit timing / pacing issues 6. /watch the final cut and review it - as a video editor for technical errors (mismatched voiceover and visuals, AI hallucinations, etc) - as a viewer (ICP). I delegate most of the review to the agent because it catches more things and keeps me out of the loop as much as possible. It also fixes any issues found in the review. That's it. This video took me 30 minutes because I have already created skills for everything I described above. Some day, this will be < 5 minutes. I just review and chat to provide direction and feedback. The skills do all the technical work. 7. /learn Extracts learnings and updates the skills. This final step is really important. It turns this process into a closed loop system that makes the next video much easier to create because all the learnings from the human-in-the-loop process get encoded into code. Skills are code too. If you want access to the skill, drop a comment, and I'll DM it to you (must be following). If you want to make AI video ads like this, DM me.
0:45

Claude Code can ship a 45-second animated explainer ad in 30 minutes. No video editor needed, just CC + skills. Here's how I made this video for Soteri Skin 👇 1. /plan Concept Brief (Claude Code) I handwrite a concept brief, then chat with the agent to iterate on it. The agent gathers any raw materials we might need - context about the brand, product images, end card, etc. The concept brief details the concept, characters, visual style, script, etc 2. /prepare a moodboard (CC + GPT Image 2 + ElevenLabs) After reviewing the script, generate: - character reference images - voiceover samples for the characters / narrator - the storyboard (scene by scene grid) - a few keyframe scenes 3. /generate Keyframes for each scene (CC uses Nano Banana or GPT Image 2) Uses the character references from the previous step to generate keyframes for each scene. I probably should have done a round of iteration at this step – there's some character drift and the pH meter representation could have been better. 4. /animate Keyframe → Animated Clip (CC uses Fal Seedance) Generate 2-4 representative scenes first to see a preview. If it looks good, then generate everything. 5. /stitch (CC + ffmpeg + ElevenLabs) - Stitch clips together with hard cut - Add a music score + SFX - Sync clips to the VO - Add captions - Review and edit timing / pacing issues 6. /watch the final cut and review it - as a video editor for technical errors (mismatched voiceover and visuals, AI hallucinations, etc) - as a viewer (ICP). I delegate most of the review to the agent because it catches more things and keeps me out of the loop as much as possible. It also fixes any issues found in the review. That's it. This video took me 30 minutes because I have already created skills for everything I described above. Some day, this will be < 5 minutes. I just review and chat to provide direction and feedback. The skills do all the technical work. 7. /learn Extracts learnings and updates the skills. This final step is really important. It turns this process into a closed loop system that makes the next video much easier to create because all the learnings from the human-in-the-loop process get encoded into code. Skills are code too. If you want access to the skill, drop a comment, and I'll DM it to you (must be following). If you want to make AI video ads like this, DM me.

Shiv

11,723 görüntüleme • 4 ay önce

3 steps story. I gave Claude $40 and it made me $8,409 in a week on Polymarket I typed a prompt. Claude wrote the bot. I funded it. $40 in. $8,409 out. 7 days. Someone else did the same thing and turned it into $294,127 in 26 days. And the prompt I used is something I've never shared publicly. Until now. This bro is a great example of how MY system looks at a scale: Profile → 0x0006af12cd4dacc450836a0e1ec6ce47365d8c63 $294,127.72 all-time. 2,226 predictions. $14,800 biggest win. Joined March 2026. 26.9K views. Still mostly unwatched. While I was developing my own script I copytraded this AI to see how profitable this strategy is, made $520 from my $10 lol Copytrade here: And every single position is the same structure. "ETH Up or Down - March 7, 11:45AM" → $1,895 in → $16,695 out +780% "BTC Up or Down - March 21, 11:20PM" → $1,186 in → $11,919 out. +904% This isn't trading. It's one equation running on loop while you sleep. Here's exactly what I typed into Claude: The prompt had 4 instructions: 1. Map temporal bias windows "Analyze 24 months of BTC and ETH hourly data. Find which specific time windows have statistically significant directional bias above 65%. Ignore all other windows." The crowd prices every window as 50/50. They're not. Claude found the ones that aren't. 2. Build Kelly sizing "Size each position using fractional Kelly. Scale conviction to statistical confidence. Never flat-size. " f* = (p × b - q) / b That's why entries look random - $259, $886, $25,002. They're not random. They're mathematically weighted. 3. Add a volatility filter "Skip any window where 24h realized volatility exceeds 1.4x the 30-day average. Patterns break in chaos." The bot doesn't fire blindly. It waits for clean mathematical conditions. 4. Bayesian self-updating "After each settled trade, update win probability for that window. The model sharpens itself." Every loss makes the next trade smarter. Every win increases conviction. Claude wrote the entire execution script in 23 minutes. I funded it with $40. It placed its first trade 4 minutes later. $40 → $8,409. One week. The wallet above ran the same logic for 26 days → $294,127. This wallet had 26.9K views before this post. Tomorrow it'll have 10x that. The people who moved first always win. Always. FOLLOW while this is still a quiet room.
0:23

3 steps story. I gave Claude $40 and it made me $8,409 in a week on Polymarket I typed a prompt. Claude wrote the bot. I funded it. $40 in. $8,409 out. 7 days. Someone else did the same thing and turned it into $294,127 in 26 days. And the prompt I used is something I've never shared publicly. Until now. This bro is a great example of how MY system looks at a scale: Profile → 0x0006af12cd4dacc450836a0e1ec6ce47365d8c63 $294,127.72 all-time. 2,226 predictions. $14,800 biggest win. Joined March 2026. 26.9K views. Still mostly unwatched. While I was developing my own script I copytraded this AI to see how profitable this strategy is, made $520 from my $10 lol Copytrade here: And every single position is the same structure. "ETH Up or Down - March 7, 11:45AM" → $1,895 in → $16,695 out +780% "BTC Up or Down - March 21, 11:20PM" → $1,186 in → $11,919 out. +904% This isn't trading. It's one equation running on loop while you sleep. Here's exactly what I typed into Claude: The prompt had 4 instructions: 1. Map temporal bias windows "Analyze 24 months of BTC and ETH hourly data. Find which specific time windows have statistically significant directional bias above 65%. Ignore all other windows." The crowd prices every window as 50/50. They're not. Claude found the ones that aren't. 2. Build Kelly sizing "Size each position using fractional Kelly. Scale conviction to statistical confidence. Never flat-size. " f* = (p × b - q) / b That's why entries look random - $259, $886, $25,002. They're not random. They're mathematically weighted. 3. Add a volatility filter "Skip any window where 24h realized volatility exceeds 1.4x the 30-day average. Patterns break in chaos." The bot doesn't fire blindly. It waits for clean mathematical conditions. 4. Bayesian self-updating "After each settled trade, update win probability for that window. The model sharpens itself." Every loss makes the next trade smarter. Every win increases conviction. Claude wrote the entire execution script in 23 minutes. I funded it with $40. It placed its first trade 4 minutes later. $40 → $8,409. One week. The wallet above ran the same logic for 26 days → $294,127. This wallet had 26.9K views before this post. Tomorrow it'll have 10x that. The people who moved first always win. Always. FOLLOW while this is still a quiet room.

Frogify

19,971 görüntüleme • 5 ay önce

The biggest leak in many people's postures is the rear muscles of the legs. They should be powerful, but long-seated days drain their strength and leave you without vital support. These 4 exercises will patch the leak. Do one 2x/week and watch your posture rise again: 1 - Lying Hyperextension (0:05) 3 x 8-10 This variation is a great place to start. - Lying on your stomach. - Lift both legs off the floor as high as possible without swinging. - Hold for 3 seconds at the top 2 - Bench Hyperextension (0:12) 3 x 8-10 This variation is great because you get a better stretch than on the floor. You can use the end of a couch or the corner of your bed instead of a bench. 3 - Bench Frog Hyperextension (0:18) 3 x 8-10 The Frog variation has both of your feet flat against each other. This position changes how your muscles execute the motion. Your glutes and hamstrings work more intensely. 4 - Weighted Bench Hyperextensions (0:24) 3 x 8-10 Add weight once you are comfortable enough to do full sets of the bodyweight variation. You'll get much better results. Your glutes and hamstrings will respond kindly and provide more postural support. // Keeping your Glutes and Hamstrings strong is essential to withstand the 21st century. Use the exercises above to protect your posture and quality of life.
0:30

The biggest leak in many people's postures is the rear muscles of the legs. They should be powerful, but long-seated days drain their strength and leave you without vital support. These 4 exercises will patch the leak. Do one 2x/week and watch your posture rise again: 1 - Lying Hyperextension (0:05) 3 x 8-10 This variation is a great place to start. - Lying on your stomach. - Lift both legs off the floor as high as possible without swinging. - Hold for 3 seconds at the top 2 - Bench Hyperextension (0:12) 3 x 8-10 This variation is great because you get a better stretch than on the floor. You can use the end of a couch or the corner of your bed instead of a bench. 3 - Bench Frog Hyperextension (0:18) 3 x 8-10 The Frog variation has both of your feet flat against each other. This position changes how your muscles execute the motion. Your glutes and hamstrings work more intensely. 4 - Weighted Bench Hyperextensions (0:24) 3 x 8-10 Add weight once you are comfortable enough to do full sets of the bodyweight variation. You'll get much better results. Your glutes and hamstrings will respond kindly and provide more postural support. // Keeping your Glutes and Hamstrings strong is essential to withstand the 21st century. Use the exercises above to protect your posture and quality of life.

Alex Bernier

256,639 görüntüleme • 2 yıl önce

How to set up Claude Cowork so it actually works like an AI chief of staff (not just another chatbot): 1. Most people open Cowork, type a message, and get generic output. It's not a Claude problem. It's a setup problem. Cowork needs context before it can help you. Who you are. How you work. What you're building. Your team. Your priorities. Give it that, and every session feels like picking up a conversation with an executive assistant. 2. The setup has three layers: a) Global instructions (who you are, how you work, what Claude should never do). b) Connectors (Slack, Gmail, Google Calendar, Notion) c) And a folder structure on your computer that acts as Claude's long-term memory. That combination is what takes it from generic to personalized. 3. Skills are the real leverage. A skill is a markdown file that tells Claude exactly how to do one thing well. Write my newsletter. Coach me on a decision. Review a case study. Each skill lives in its own folder with context, examples, and a definition of what success looks like. 4. We built a CEO coach skill in the video below. Gave it business context, leadership style, company goals. Then tested it with a real decision: should we increase our newsletter from once to twice a week? It came back with trade-offs, second-order consequences, and risk assessment. 5. Then we built a multi-agent advisory board. Five subagents, each with a defined persona: a) the operator b) the skeptic c) the customer advocate d) the finance partner e) the legal/risk advisor. You feed it a decision. Each agent evaluates independently. The main agent synthesizes the feedback. It's like having a board meeting on demand. 6. Third skill: a thought leadership content pipeline. Topic scoring, idea capture, distribution cadence, tone calibration. All built from your actual expertise and audience. Designed so an executive can go from idea to published post without starting from scratch every time. 7. The workspace map is what ties it all together. It's a top-level file that shows Claude how to navigate your entire setup. Which folders exist, what skills live where, how to invoke them. Without it, Claude has to search for everything. With it, Claude goes straight to what it needs. 8. Everything you build is portable. The folder structure works in Cowork, Claude Code, and Codex. Push it to a private GitHub repo and you can access it from your phone through Claude Code, or use Claude Dispatch. 9. The pattern is repeatable. Pick a task you do often. Create a folder. Build a skill. Add examples of what success looks like, and what a bad output looks like. Test it. Workshop it. Move on to the next one. Each skill is like onboarding a new employee who never forgets and never needs to be re-trained. The people who invest in this setup now are the ones who will have a 10x advantage when these tools get even better. And they're getting better fast. I sat down with Alex Lieberman on Human In The Loop and we built all three of these live from scratch. Full breakdown in the video below.. I tried to explain this as clear as possible for my non-developer crowd. Send it to someone who should be using Cowork but isn't yet. Or bookmark it to level up when you're ready. Watch 👇🏼
51:23

How to set up Claude Cowork so it actually works like an AI chief of staff (not just another chatbot): 1. Most people open Cowork, type a message, and get generic output. It's not a Claude problem. It's a setup problem. Cowork needs context before it can help you. Who you are. How you work. What you're building. Your team. Your priorities. Give it that, and every session feels like picking up a conversation with an executive assistant. 2. The setup has three layers: a) Global instructions (who you are, how you work, what Claude should never do). b) Connectors (Slack, Gmail, Google Calendar, Notion) c) And a folder structure on your computer that acts as Claude's long-term memory. That combination is what takes it from generic to personalized. 3. Skills are the real leverage. A skill is a markdown file that tells Claude exactly how to do one thing well. Write my newsletter. Coach me on a decision. Review a case study. Each skill lives in its own folder with context, examples, and a definition of what success looks like. 4. We built a CEO coach skill in the video below. Gave it business context, leadership style, company goals. Then tested it with a real decision: should we increase our newsletter from once to twice a week? It came back with trade-offs, second-order consequences, and risk assessment. 5. Then we built a multi-agent advisory board. Five subagents, each with a defined persona: a) the operator b) the skeptic c) the customer advocate d) the finance partner e) the legal/risk advisor. You feed it a decision. Each agent evaluates independently. The main agent synthesizes the feedback. It's like having a board meeting on demand. 6. Third skill: a thought leadership content pipeline. Topic scoring, idea capture, distribution cadence, tone calibration. All built from your actual expertise and audience. Designed so an executive can go from idea to published post without starting from scratch every time. 7. The workspace map is what ties it all together. It's a top-level file that shows Claude how to navigate your entire setup. Which folders exist, what skills live where, how to invoke them. Without it, Claude has to search for everything. With it, Claude goes straight to what it needs. 8. Everything you build is portable. The folder structure works in Cowork, Claude Code, and Codex. Push it to a private GitHub repo and you can access it from your phone through Claude Code, or use Claude Dispatch. 9. The pattern is repeatable. Pick a task you do often. Create a folder. Build a skill. Add examples of what success looks like, and what a bad output looks like. Test it. Workshop it. Move on to the next one. Each skill is like onboarding a new employee who never forgets and never needs to be re-trained. The people who invest in this setup now are the ones who will have a 10x advantage when these tools get even better. And they're getting better fast. I sat down with Alex Lieberman on Human In The Loop and we built all three of these live from scratch. Full breakdown in the video below.. I tried to explain this as clear as possible for my non-developer crowd. Send it to someone who should be using Cowork but isn't yet. Or bookmark it to level up when you're ready. Watch 👇🏼

JJ Englert

574,377 görüntüleme • 6 ay önce

Thariq Shihipar (Thariq) is an engineer on Anthropic’s Claude Code team I asked him how Anthropic makes the most out of the models for engineering and how the industry will change soon. In this episode: • Internal best practices in leveraging the models • What percent of Anthropic's work is fully autonomous • How Anthropic maintains higher volumes of code • What has worked in preventing AI-written breakages Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsor of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at Chapters: 00:00 Intro 00:29 Onboarding at Anthropic 02:53 Internal capabilities vs external perception 06:16 Model vs Harness 08:55 What percent of Anthropics changes are fully autonomous 14:51 Computer use 17:42 How to make the most out of your compute 20:45 Loop engineering 22:47 Where the industry will go soon 26:02 Which model do Anthropic engineers use 27:38 Is learning a particular model worth it 30:56 Prompting tips for todays models 35:04 How to get the models to do tasteful work 39:00 How much of writing is done by AI at Anthropic 45:36 Code ownership and maintenance at Anthropic 52:04 How Anthropic prevents breakages 55:24 Visibility and sharing your work 58:42 Luck surface area example 01:00:57 Should people still learn to code 01:07:42 Advice for his younger self 01:09:58 Outro
1:10:54

Thariq Shihipar (Thariq) is an engineer on Anthropic’s Claude Code team I asked him how Anthropic makes the most out of the models for engineering and how the industry will change soon. In this episode: • Internal best practices in leveraging the models • What percent of Anthropic's work is fully autonomous • How Anthropic maintains higher volumes of code • What has worked in preventing AI-written breakages Where to watch: • YouTube - • Spotify - • Apple Podcasts - • Transcript - Thank you to the sponsor of this episode for supporting my work: • WorkOS: makes your app Enterprise Ready with easy to use APIs to add SSO, SCIM, RBAC, and more in just a few lines of code, check them out at Chapters: 00:00 Intro 00:29 Onboarding at Anthropic 02:53 Internal capabilities vs external perception 06:16 Model vs Harness 08:55 What percent of Anthropics changes are fully autonomous 14:51 Computer use 17:42 How to make the most out of your compute 20:45 Loop engineering 22:47 Where the industry will go soon 26:02 Which model do Anthropic engineers use 27:38 Is learning a particular model worth it 30:56 Prompting tips for todays models 35:04 How to get the models to do tasteful work 39:00 How much of writing is done by AI at Anthropic 45:36 Code ownership and maintenance at Anthropic 52:04 How Anthropic prevents breakages 55:24 Visibility and sharing your work 58:42 Luck surface area example 01:00:57 Should people still learn to code 01:07:42 Advice for his younger self 01:09:58 Outro

Ryan Peterman

65,784 görüntüleme • 16 gün önce

Some stories are too painful to watch. But this one? It was too painful to write. Omoshalewa was in law school when her life was first interrupted in 2014. What started as a sharp stomach pain quickly turned into an ovarian cyst and a hospital that left her on a bench, unattended for hours. Since then, she’s had 14 surgeries. Fourteen. Each one promised relief. Each one offered a bit of hope. But the pain always came back stronger, stranger, harder to name. By 2021, she was being injected with Kenalog-40 daily which led to her skin changing and her memory declining. Later on, she found out that she had Cushing’s Syndrome: A result of long-term steroid overuse. She passed out in her sleep, choked on saliva and developed necrosis in both hips. But through it all? She kept working, asking questions and more. What struck me most wasn’t just the trauma. It was how often she was dismissed, told to pray more and told that her symptoms were imaginary. Omoshalewa’s story is not rare. That’s the part that should scare us. Because beneath the medical errors and systemic failures… Is a young woman who just wanted to breathe without pain. We talk about reform. But real reform starts with respect. With humility. With care that doesn’t punish people for surviving. If you’re a health worker reading this, I hope it reminds you that every patient has a story. And sometimes, their life depends on whether you listen. Find the full video on Aproko Doctor TV on Youtube
1:37

Some stories are too painful to watch. But this one? It was too painful to write. Omoshalewa was in law school when her life was first interrupted in 2014. What started as a sharp stomach pain quickly turned into an ovarian cyst and a hospital that left her on a bench, unattended for hours. Since then, she’s had 14 surgeries. Fourteen. Each one promised relief. Each one offered a bit of hope. But the pain always came back stronger, stranger, harder to name. By 2021, she was being injected with Kenalog-40 daily which led to her skin changing and her memory declining. Later on, she found out that she had Cushing’s Syndrome: A result of long-term steroid overuse. She passed out in her sleep, choked on saliva and developed necrosis in both hips. But through it all? She kept working, asking questions and more. What struck me most wasn’t just the trauma. It was how often she was dismissed, told to pray more and told that her symptoms were imaginary. Omoshalewa’s story is not rare. That’s the part that should scare us. Because beneath the medical errors and systemic failures… Is a young woman who just wanted to breathe without pain. We talk about reform. But real reform starts with respect. With humility. With care that doesn’t punish people for surviving. If you’re a health worker reading this, I hope it reminds you that every patient has a story. And sometimes, their life depends on whether you listen. Find the full video on Aproko Doctor TV on Youtube

Dr. Chinonso Egemba

24,690 görüntüleme • 1 yıl önce

BROKEN HALLELUYAH is one movie I recommend to everyone irrespective of religion… On Monday 4th June 2016 around 10am, our 1-year marriage anniversary, my wife called me & was literally sobbing on the phone. 2 things break me on the instant & could make me cry - my wife in tears & my kids in pain. She called telling me she was tired & why has God not given us a baby. I felt her pain, pulse, tears & I had shivers all over. I didn’t know what to say. Now, you could say it’s just one year, how about those who had to wait for donkey years; but not everyone has the strength for a long period of waiting. God has said He would not make us go through what is beyond our strength. One thing you must understand each time you are going through a tough time is that God is aware & He knows you have the strength to go through it till your miracle comes. As she dropped the call, I knew this woman doesn’t have strength for a long wait. I walked into the empty board room, knelt down & I cried out to God begging Him that for the sake of my wife, He should just give us a baby. I don’t have issues as it’s just 1-year & it could very well happen within the 2nd year, but this isn’t about me cos I don’t know what this would further do to her, as she isn’t so mentally rugged like that. Just about a 10-minute heartfelt prayer to God. That very week, my wife conceived & we welcomed our bundle of joy 9 months later. Truth is that we go through these tough moments, not to break us or to punish us, but to make us better people. Today, my wife is one of the toughest women I know. Sometimes she lifts me when I’m down.
4:59

BROKEN HALLELUYAH is one movie I recommend to everyone irrespective of religion… On Monday 4th June 2016 around 10am, our 1-year marriage anniversary, my wife called me & was literally sobbing on the phone. 2 things break me on the instant & could make me cry - my wife in tears & my kids in pain. She called telling me she was tired & why has God not given us a baby. I felt her pain, pulse, tears & I had shivers all over. I didn’t know what to say. Now, you could say it’s just one year, how about those who had to wait for donkey years; but not everyone has the strength for a long period of waiting. God has said He would not make us go through what is beyond our strength. One thing you must understand each time you are going through a tough time is that God is aware & He knows you have the strength to go through it till your miracle comes. As she dropped the call, I knew this woman doesn’t have strength for a long wait. I walked into the empty board room, knelt down & I cried out to God begging Him that for the sake of my wife, He should just give us a baby. I don’t have issues as it’s just 1-year & it could very well happen within the 2nd year, but this isn’t about me cos I don’t know what this would further do to her, as she isn’t so mentally rugged like that. Just about a 10-minute heartfelt prayer to God. That very week, my wife conceived & we welcomed our bundle of joy 9 months later. Truth is that we go through these tough moments, not to break us or to punish us, but to make us better people. Today, my wife is one of the toughest women I know. Sometimes she lifts me when I’m down.

DON “Tobechukwu” Ade 👑

52,230 görüntüleme • 1 yıl önce

Figured I’d make a little different post as I did some racing myself last week! I’m coming down off an incredible week Tour of the Gila where I raced in the cat 1 field. I won a stage (yes crazy!), finished 5th overall (also crazy), and won the masters cat 1 40+ overall over Italian legend Fortunato Ferrara. Now after having sometime to reflect I want to share some of the thoughts I had from the race. 1. Family made the racing experience so special for me. I’ve done a lot of bike races, but this one was so good having much of the family together for it. @kourtneydanielson was there keeping me on track, @stevedanielson237 was there grinding in his race at the same time, @alpha_zulu_6 was in “no-fail mission mode” running the race logistics, and Sarah was there inspiring us to dig deep. We just need @stelladdanielson for the next one with the little ones and watch out world! 2. To win you have to be ready to lose. I’ll be honest, racing has so much trauma around it for me I have a long ways to go to really enjoy it, but I am getting there. But what I did “re-experience” was how if you are worried about winning you will often paralyze yourself and not be able to give what it takes. I did have moments where I completely locked into “racing” and just enjoyed going for it. 3. You don’t have to feel well to do well. As a coach I preach this one all the time but man, I really felt it this week. I got that gnarly sinus virus going around and wow, does it bite hard. I really struggled each day on the bike and off the bike I spent wayyyyy too much time worrying about what was going to happen in the bike. Kourtney came to the rescue to keep sending me back out there despite me trying to negotiate with her to sit it out. Wow, I was so glad I did listen to her! 4. The future is bright. Let me tell you, there is some big talent out there coming. I got to race with a lot of the young pros and I also got to hear about the talent coming from my son’s field. There were 5 riders I saw in my race that were all u23 and absolutely could make it to the World Tour. This race always brings talent out, but I would say there is more than in the past this year. I hope these riders keep working hard and team up with someone who actually knows how to get to the world tour. There’s so much to build and the right progression is everything. 5. I’m not done yet. This week was just the beginning of a new chapter for me. Back to work!
0:41

Figured I’d make a little different post as I did some racing myself last week! I’m coming down off an incredible week Tour of the Gila where I raced in the cat 1 field. I won a stage (yes crazy!), finished 5th overall (also crazy), and won the masters cat 1 40+ overall over Italian legend Fortunato Ferrara. Now after having sometime to reflect I want to share some of the thoughts I had from the race. 1. Family made the racing experience so special for me. I’ve done a lot of bike races, but this one was so good having much of the family together for it. @kourtneydanielson was there keeping me on track, @stevedanielson237 was there grinding in his race at the same time, @alpha_zulu_6 was in “no-fail mission mode” running the race logistics, and Sarah was there inspiring us to dig deep. We just need @stelladdanielson for the next one with the little ones and watch out world! 2. To win you have to be ready to lose. I’ll be honest, racing has so much trauma around it for me I have a long ways to go to really enjoy it, but I am getting there. But what I did “re-experience” was how if you are worried about winning you will often paralyze yourself and not be able to give what it takes. I did have moments where I completely locked into “racing” and just enjoyed going for it. 3. You don’t have to feel well to do well. As a coach I preach this one all the time but man, I really felt it this week. I got that gnarly sinus virus going around and wow, does it bite hard. I really struggled each day on the bike and off the bike I spent wayyyyy too much time worrying about what was going to happen in the bike. Kourtney came to the rescue to keep sending me back out there despite me trying to negotiate with her to sit it out. Wow, I was so glad I did listen to her! 4. The future is bright. Let me tell you, there is some big talent out there coming. I got to race with a lot of the young pros and I also got to hear about the talent coming from my son’s field. There were 5 riders I saw in my race that were all u23 and absolutely could make it to the World Tour. This race always brings talent out, but I would say there is more than in the past this year. I hope these riders keep working hard and team up with someone who actually knows how to get to the world tour. There’s so much to build and the right progression is everything. 5. I’m not done yet. This week was just the beginning of a new chapter for me. Back to work!

tom danielson

11,973 görüntüleme • 4 ay önce

🚨NEW EPISODE🚨 WHY BUY GOLD & SILVER? “This is about being short the behaviour of your government. If you think they're going to be disciplined & they're going to raise rates above inflation & give you a real return on your cash, then don't do it.” This week on The Master Investor Podcast I am joined by Ned Naylor Leyland – Manager of $3bn Jupiter Gold & Silver Fund, & recently crowned Investment Week Fund Manager Of The Year. “You can ask yourself – the Treasury Secretary & the Fed Chair, are they politicians? I mean in my view, absolutely. I mean the idea of independence in my view is rather fanciful – these people say one thing & do another. The idea that there'll be a genuine pullback in the scale of central bank balance sheets is in my view unlikely.” GOLD MINERS: “The producers have never been cheaper than they are today. Ever. So these are the most profitable companies in the world - 50% free cashflow margin is probably double & in some cases triple the free cashflow that tech is making.” SILVER: "Silver is like gold in that you are short politicians, but you're also long the future. So your long green tech, tech, the military, everything really that's running the modern economy, but you're also short politicians. So silver has a nice dual feel to it.” IF TECH SELLS OFF? “It's very likely that if the equity market does go lower, then that creates a more dovish background, which is the fuel for the space I invest in. So you see a very big decoupling then of performance between the wider equity market & this particular part of it.” BITCOIN: "My personal investment style is I want to be early & I don't want to be there for the last two months of the pregnancy. I'd rather be there right at the beginning & then once I reach the point where other people are starting to get excited & jump in & there's a kind of critical mass feel, that doesn't make me feel comfortable. This is a genuine contrarian thing where I don't want to be there." GOLD vs BITCOIN: "You own gold & silver because you are thinking about this over the long term, whereas you might want to trade Bitcoin as a way to fund your holiday." WHERE IS THE GOLD: “Should these bars be audited? They should also be checked for encumbrances, which is really the more important point, presuming they're all there, who owns them? How many times over have they been leased, loaned, swapped into the system? There's one thing that is there. The other thing is how many post-it notes on each bar?" Timestamps: 0:00 Intro 3:05 Long term case for gold 6:14 Long term case for silver 7:06 Why no other metals? 9:54 What drove 2025 surge in gold & silver 13:06 Did Gold peak in January? 15:20 Is debasement priced in? 17:15 Central banks are NOT independent 22:00 Gold not risk-on or risk-off – its risk-free 23:15 Gold vs Bitcoin 27:14 Physical commodity + producers + development assets 29:52 Miners cheaper than ever 33:10 Portfolio construction 34:56 Gold & Silver not normal commodities 37:25 Where Is The Gold? 42:26 Physical gold vs his fund? 43:40 Revaluation of US gold reserves? 50:13 Why buy gold & silver NOW? 51:47 Could governments behave? 54:37 Conclusion
56:31

🚨NEW EPISODE🚨 WHY BUY GOLD & SILVER? “This is about being short the behaviour of your government. If you think they're going to be disciplined & they're going to raise rates above inflation & give you a real return on your cash, then don't do it.” This week on The Master Investor Podcast I am joined by Ned Naylor Leyland – Manager of $3bn Jupiter Gold & Silver Fund, & recently crowned Investment Week Fund Manager Of The Year. “You can ask yourself – the Treasury Secretary & the Fed Chair, are they politicians? I mean in my view, absolutely. I mean the idea of independence in my view is rather fanciful – these people say one thing & do another. The idea that there'll be a genuine pullback in the scale of central bank balance sheets is in my view unlikely.” GOLD MINERS: “The producers have never been cheaper than they are today. Ever. So these are the most profitable companies in the world - 50% free cashflow margin is probably double & in some cases triple the free cashflow that tech is making.” SILVER: "Silver is like gold in that you are short politicians, but you're also long the future. So your long green tech, tech, the military, everything really that's running the modern economy, but you're also short politicians. So silver has a nice dual feel to it.” IF TECH SELLS OFF? “It's very likely that if the equity market does go lower, then that creates a more dovish background, which is the fuel for the space I invest in. So you see a very big decoupling then of performance between the wider equity market & this particular part of it.” BITCOIN: "My personal investment style is I want to be early & I don't want to be there for the last two months of the pregnancy. I'd rather be there right at the beginning & then once I reach the point where other people are starting to get excited & jump in & there's a kind of critical mass feel, that doesn't make me feel comfortable. This is a genuine contrarian thing where I don't want to be there." GOLD vs BITCOIN: "You own gold & silver because you are thinking about this over the long term, whereas you might want to trade Bitcoin as a way to fund your holiday." WHERE IS THE GOLD: “Should these bars be audited? They should also be checked for encumbrances, which is really the more important point, presuming they're all there, who owns them? How many times over have they been leased, loaned, swapped into the system? There's one thing that is there. The other thing is how many post-it notes on each bar?" Timestamps: 0:00 Intro 3:05 Long term case for gold 6:14 Long term case for silver 7:06 Why no other metals? 9:54 What drove 2025 surge in gold & silver 13:06 Did Gold peak in January? 15:20 Is debasement priced in? 17:15 Central banks are NOT independent 22:00 Gold not risk-on or risk-off – its risk-free 23:15 Gold vs Bitcoin 27:14 Physical commodity + producers + development assets 29:52 Miners cheaper than ever 33:10 Portfolio construction 34:56 Gold & Silver not normal commodities 37:25 Where Is The Gold? 42:26 Physical gold vs his fund? 43:40 Revaluation of US gold reserves? 50:13 Why buy gold & silver NOW? 51:47 Could governments behave? 54:37 Conclusion

Wilfred Frost

80,971 görüntüleme • 3 ay önce

BREAKING: Legendary cartoonist Scott Adams has passed away and his ex-wife reads his final message to followers telling them that he accepted Jesus Christ as his Lord and Savior. If Scott Adams had an impact on your life, this will be the most heartbreaking six and a half minutes you’ll listen to. Shelly Adams read Scott’s final words while holding back tears, live from the very place where he used to stream: “Unfortunately, this isn’t good news.” “Of course, he waited till just before the show started. But he’s not with us anymore. I’m going to try to get through this. He has a final message that he wanted to say. So I’m going to try to read it. Trying to be strong.” “If you are reading this, things did not go well for me. I have a few things to say before I go.” “My body failed before my brain. I am of sound mind as I write this, January 1st, 2026.” “Many of my Christian friends have asked me to find Jesus before I go. I’m not a believer, but I have to admit, the risk reward calculation for doing so looks so attractive to me.” “So here I go. I accept Jesus Christ as my Lord and Savior and look forward to spending an eternity with him. The part about me not being a believer should be quite quickly resolved if I wake up in heaven.” “I won’t need any more convincing than that. I hope I’m still qualified for entry.” “With your permission, I’d like to explain my life.” “For the first part of my life, I was focused on making myself a worthy husband and parent, as a way of to find meaning. That worked. But marriages don’t always last forever, and mine eventually ended in a highly amicable way. I’m grateful for those years and for the people I came to call my family.” “Once the marriage unwound, I needed a new focus, a new meaning. And so I donated myself to the world. Literally speaking the words out loud in my otherwise, silent home.” “From that point on, I looked for ways I could add the most to people’s life one way or another. That marked the start of my evolution from Dilbert cartoonist to an author of what I hoped would be useful books.” “By then, I believe, I had enough life lessons that I could start passing them on. I continued making Dilbert comics, of course. As luck would have it, I’m a good writer.” “My book in the useful category was How to Fail at Almost Everything and Still Win Big. The book turned out to be a huge success, often imitated and influenced a wide variety of people.” “I still hear every day how much the book change lives. My plan to be useful was working.” “I followed up with my book Win Bigly. That trained an army of citizens how to be more persuasive. Which that correctly saw as a minor superpower. I know the book change lives because I hear it often.” “You probably never know the impact the book had on the world, but I know, and it pleases me while giving me a sense of meaning that is impossible to describe.” “My next book, Loser Think, tried to teach people how to think better, especially if they were to explain their thinking on social media. That one didn’t put much of a dent in the universe, but I tried.” “Finally, my book, Reframe Your Brain, taught readers how to program their own thoughts to make their personal and professional lives better. I was surprised and delighted at how much positive input impact the book is having.” “I also started podcasting a live show called Coffee With Scott Adams, dedicated to helping people think about the world and their lives in a more productive way. I didn’t plan it this way, but it ended up helping lots of lonely people find a community that made them less lonely.” “Again, that had great meaning to me.” “I had an amazing life.” “I gave it everything I had.” “If I got any benefits from my work, I’m asking that you pay it forward as best as you can.” “That’s the legacy I want. Be useful and please know I loved you all to the very end, Scott Adams.”
6:23

BREAKING: Legendary cartoonist Scott Adams has passed away and his ex-wife reads his final message to followers telling them that he accepted Jesus Christ as his Lord and Savior. If Scott Adams had an impact on your life, this will be the most heartbreaking six and a half minutes you’ll listen to. Shelly Adams read Scott’s final words while holding back tears, live from the very place where he used to stream: “Unfortunately, this isn’t good news.” “Of course, he waited till just before the show started. But he’s not with us anymore. I’m going to try to get through this. He has a final message that he wanted to say. So I’m going to try to read it. Trying to be strong.” “If you are reading this, things did not go well for me. I have a few things to say before I go.” “My body failed before my brain. I am of sound mind as I write this, January 1st, 2026.” “Many of my Christian friends have asked me to find Jesus before I go. I’m not a believer, but I have to admit, the risk reward calculation for doing so looks so attractive to me.” “So here I go. I accept Jesus Christ as my Lord and Savior and look forward to spending an eternity with him. The part about me not being a believer should be quite quickly resolved if I wake up in heaven.” “I won’t need any more convincing than that. I hope I’m still qualified for entry.” “With your permission, I’d like to explain my life.” “For the first part of my life, I was focused on making myself a worthy husband and parent, as a way of to find meaning. That worked. But marriages don’t always last forever, and mine eventually ended in a highly amicable way. I’m grateful for those years and for the people I came to call my family.” “Once the marriage unwound, I needed a new focus, a new meaning. And so I donated myself to the world. Literally speaking the words out loud in my otherwise, silent home.” “From that point on, I looked for ways I could add the most to people’s life one way or another. That marked the start of my evolution from Dilbert cartoonist to an author of what I hoped would be useful books.” “By then, I believe, I had enough life lessons that I could start passing them on. I continued making Dilbert comics, of course. As luck would have it, I’m a good writer.” “My book in the useful category was How to Fail at Almost Everything and Still Win Big. The book turned out to be a huge success, often imitated and influenced a wide variety of people.” “I still hear every day how much the book change lives. My plan to be useful was working.” “I followed up with my book Win Bigly. That trained an army of citizens how to be more persuasive. Which that correctly saw as a minor superpower. I know the book change lives because I hear it often.” “You probably never know the impact the book had on the world, but I know, and it pleases me while giving me a sense of meaning that is impossible to describe.” “My next book, Loser Think, tried to teach people how to think better, especially if they were to explain their thinking on social media. That one didn’t put much of a dent in the universe, but I tried.” “Finally, my book, Reframe Your Brain, taught readers how to program their own thoughts to make their personal and professional lives better. I was surprised and delighted at how much positive input impact the book is having.” “I also started podcasting a live show called Coffee With Scott Adams, dedicated to helping people think about the world and their lives in a more productive way. I didn’t plan it this way, but it ended up helping lots of lonely people find a community that made them less lonely.” “Again, that had great meaning to me.” “I had an amazing life.” “I gave it everything I had.” “If I got any benefits from my work, I’m asking that you pay it forward as best as you can.” “That’s the legacy I want. Be useful and please know I loved you all to the very end, Scott Adams.”

Overton

55,478 görüntüleme • 8 ay önce

A lot of people think that if you’re carnivore, you must be anti-plants. I’m not anti-plants. There are millions of people in the world who eat plants and do great on them. Some plants are absolutely fine for some bodies. Right now they’re not fine for mine. That’s why I use carnivore as an elimination protocol. When I started, I had inflammation, digestive issues, likely SIBO, leaky gut, and a system that felt chaotic. I didn’t know what foods were helping and what foods were hurting me. When you’re eating a bunch of different plant foods every week, it’s almost impossible to figure out what’s causing the problem. Carnivore removes the noise. Beef, butter, bacon, eggs, salt, water. That’s it. Once the noise is gone, your body finally has a chance to tell the truth. Over the last 13 months I’ve tested a few plants one at a time like zucchini, cucumber, raspberries, strawberries, and pickles. I paid attention to how I felt after each one. That’s how you collect useful data. Not guesses. Data. A lot of people try keto and don’t feel much different, so they assume eating more meat and cutting carbs “didn’t work.” But many times they’re still eating the same plants that were triggering inflammation in the first place. Not always. But often enough that it matters. If your system is reacting to something you’re eating, keto can lower carbs without actually removing the trigger. Carnivore does. This isn’t for everyone. But if your joints hurt, your digestion is unpredictable, your sleep is off, or your inflammation feels constant, a 90-day carnivore elimination phase can give you answers fast. Remove the variables. Watch what changes. Then add foods back one at a time and see what your body actually tolerates. That’s not restriction. That’s investigation.
2:37

A lot of people think that if you’re carnivore, you must be anti-plants. I’m not anti-plants. There are millions of people in the world who eat plants and do great on them. Some plants are absolutely fine for some bodies. Right now they’re not fine for mine. That’s why I use carnivore as an elimination protocol. When I started, I had inflammation, digestive issues, likely SIBO, leaky gut, and a system that felt chaotic. I didn’t know what foods were helping and what foods were hurting me. When you’re eating a bunch of different plant foods every week, it’s almost impossible to figure out what’s causing the problem. Carnivore removes the noise. Beef, butter, bacon, eggs, salt, water. That’s it. Once the noise is gone, your body finally has a chance to tell the truth. Over the last 13 months I’ve tested a few plants one at a time like zucchini, cucumber, raspberries, strawberries, and pickles. I paid attention to how I felt after each one. That’s how you collect useful data. Not guesses. Data. A lot of people try keto and don’t feel much different, so they assume eating more meat and cutting carbs “didn’t work.” But many times they’re still eating the same plants that were triggering inflammation in the first place. Not always. But often enough that it matters. If your system is reacting to something you’re eating, keto can lower carbs without actually removing the trigger. Carnivore does. This isn’t for everyone. But if your joints hurt, your digestion is unpredictable, your sleep is off, or your inflammation feels constant, a 90-day carnivore elimination phase can give you answers fast. Remove the variables. Watch what changes. Then add foods back one at a time and see what your body actually tolerates. That’s not restriction. That’s investigation.

Queen of Carni

11,751 görüntüleme • 4 ay önce

If your MCP server has dozens of tools, it’s probably built wrong. You need tools that are specific and clear for each use case—but you also can’t have too many. This creates an almost impossible tradeoff that most companies don’t know how to solve. That’s why I interviewed my friend Alex Rattray (Alex Rattray), the founder and CEO of Stainless. Stainless builds APIs, SDKs, and MCP servers for companies like OpenAI and Anthropic. Alex has spent years mastering how to make software talk to software, and he came on the show to share what he knows. I had him on Every 📧’s AI & I to talk about MCP and the future of the AI-native internet. We get into: • Design MCP servers to be lean and precise. Alex’s best practices for building reliable MCP servers start with keeping the toolset small, giving each tool a precise name and description, and minimizing the inputs and outputs the model has to handle. At Stainless, they also often add a JSON filter on top to strip out unnecessary data. • Make complex APIs manageable with dynamic mode. To solve the problem of how an AI figures out which tool to use in larger APIs, Stainless switches to “dynamic mode,” where the model gets only three tools: List the endpoints, pick one and learn about it, and then execute it. • MCP servers as business copilots. At Stainless, Alex uses MCP servers to connect tools like Notion and HubSpot, so he can ask questions like, “Which customers signed up last week?” The system queries multiple databases and returns a summary that would’ve otherwise taken multiple logins and searches. • Create a “brain” for your company with Claude Code. Alex built a shared company brain at Stainless by keeping Claude Code running on his system and asking it to save useful inputs—like customer feedback and SQL queries—into GitHub. Over time, this creates a curated archive his team can query easily. • The future of MCP is code execution. Instead of giving models hundreds of tools, Alex believes the most powerful setup will be a simple code execution tool and a doc search tool. The AI writes code against an API’s SDK, runs it on a server, and checks the docs when it gets stuck. This is a must-watch for anyone who wants to understand MCP—and learn how to use them as a competitive edge. Watch below! Timestamps: Introduction: 00:01:14 Why Alex likes running barefoot: 00:02:54 APIs and MCP, the connectors of the new internet: 00:05:09 Why MCP servers are hard to get right: 00:10:53 Design principles for reliable MCP servers: 00:20:07 Scaling MCP servers for large APIs: 00:23:50 Using MCP for business ops at Stainless: 00:25:14 Building a company brain with Claude Code: 00:28:12 Where MCP goes from here: 00:33:59 Alex’s take on the security model for MCP: 00:41:10
51:39

If your MCP server has dozens of tools, it’s probably built wrong. You need tools that are specific and clear for each use case—but you also can’t have too many. This creates an almost impossible tradeoff that most companies don’t know how to solve. That’s why I interviewed my friend Alex Rattray (Alex Rattray), the founder and CEO of Stainless. Stainless builds APIs, SDKs, and MCP servers for companies like OpenAI and Anthropic. Alex has spent years mastering how to make software talk to software, and he came on the show to share what he knows. I had him on Every 📧’s AI & I to talk about MCP and the future of the AI-native internet. We get into: • Design MCP servers to be lean and precise. Alex’s best practices for building reliable MCP servers start with keeping the toolset small, giving each tool a precise name and description, and minimizing the inputs and outputs the model has to handle. At Stainless, they also often add a JSON filter on top to strip out unnecessary data. • Make complex APIs manageable with dynamic mode. To solve the problem of how an AI figures out which tool to use in larger APIs, Stainless switches to “dynamic mode,” where the model gets only three tools: List the endpoints, pick one and learn about it, and then execute it. • MCP servers as business copilots. At Stainless, Alex uses MCP servers to connect tools like Notion and HubSpot, so he can ask questions like, “Which customers signed up last week?” The system queries multiple databases and returns a summary that would’ve otherwise taken multiple logins and searches. • Create a “brain” for your company with Claude Code. Alex built a shared company brain at Stainless by keeping Claude Code running on his system and asking it to save useful inputs—like customer feedback and SQL queries—into GitHub. Over time, this creates a curated archive his team can query easily. • The future of MCP is code execution. Instead of giving models hundreds of tools, Alex believes the most powerful setup will be a simple code execution tool and a doc search tool. The AI writes code against an API’s SDK, runs it on a server, and checks the docs when it gets stuck. This is a must-watch for anyone who wants to understand MCP—and learn how to use them as a competitive edge. Watch below! Timestamps: Introduction: 00:01:14 Why Alex likes running barefoot: 00:02:54 APIs and MCP, the connectors of the new internet: 00:05:09 Why MCP servers are hard to get right: 00:10:53 Design principles for reliable MCP servers: 00:20:07 Scaling MCP servers for large APIs: 00:23:50 Using MCP for business ops at Stainless: 00:25:14 Building a company brain with Claude Code: 00:28:12 Where MCP goes from here: 00:33:59 Alex’s take on the security model for MCP: 00:41:10

Dan Shipper 📧

15,645 görüntüleme • 11 ay önce

Revel Founder & CEO Scott Morton spent 9 years working at SpaceX / Starship for Elon Musk: Biggest lesson? "Elon Musk is really good at is asking engineers to go further than they otherwise would have." i.e. Push past the first “no.” - Avoid incremental thinking. - Question every requirement & constraint. - Force one more round of thinking. - Breakthroughs often follow discomfort. Ref: Walter Isaacson's Biography on Elon: “1. Question every requirement. Each should come with the name of the person who made it. You should never accept that a requirement came from a department, such as from “the legal department” or “the safety department.” You need to know the name of the real person who made that requirement. Then you should question it, no matter how smart that person is. Requirements from smart people are the most dangerous, because people are less likely to question them. Always do so, even if the requirement came from me. Then make the requirements less dumb. 2. Delete any part or process you can. You may have to add them back later. In fact, if you do not end up adding back at least 10% of them, then you didn’t delete enough. 3. Simplify & optimize. This should come after step two. A common mistake is to simplify and optimize a part or a process that should not exist. 4. Accelerate cycle time. Every process can be speeded up. But only do this after you have followed the first three steps. In the Tesla factory, I mistakenly spent a lot of time accelerating processes that I later realized should have been deleted. 5. Automate. That comes last. The big mistake in Nevada and at Fremont was that I began by trying to automate every step. We should have waited until all the requirements had been questioned, parts and processes deleted, and the bugs were shaken out.” . . . Scott Morton (Scott Morton) Founder & CEO of Revel () "Oh man, I have so many stories. But actually, there’s a good one here. I think what Elon’s really good at is asking engineers to go further than they otherwise would have. One of the most interesting examples was the first orbital flight of Starship. We had this maneuver to separate the booster from the ship. We called it the “twig snap.” It essentially looked like a twig snapping in space, and it was a very inefficient way to do it. For the next flight, he was like, “We’re going to do hot staging,” which is where you literally start the Starship engines while it’s still connected to the booster and just blast off. Coming out of that, we all thought, “Okay, cool. We’re going to do the same exact conceptual operations for the next flight. Of course. We’re just going to go nail it this time, right?” And he was like, “No, we’re going to do hot staging on the next flight.” I was actually sitting outside. I wasn’t in the Elon meeting, but I was outside. I saw everyone walk out, and they were all just like, “Oh my God. How are we going to do this?” That week, screenshots started getting shot around. I’m sure everyone was thinking, “Oh, this is going to be really difficult.” But then, throughout the course of the week, some really awesome ideas started coming up. It started to look more and more feasible. Then it became, “How would you manufacture this? How would this all go together?” They ended up inventing, just out of nowhere, a new stage that would sit between the booster and the ship called the hot stage. It would take the blast, and then it would get ejected on reentry for the booster. It worked first shot. That’s insane. I just remember the vibes at SpaceX were like, “Oh my… how in the hell are we going to go do this?” But I think the big lesson there, and something I’ve pulled forward to Revel, is that when engineers come to you and say, “Hey, we just can’t get this to work. This is not possible,” you push them and say, “Well, why don’t you spend two more days thinking about it? Let’s see what comes up. And if nothing, we’ll think about it then.” Engineers really underestimate their ability to creatively problem-solve and come up with new ideas they otherwise never would have thought of when they’re presenting what they think is possible in the moment. I’ll say, “Okay.” They’ll say, “This just isn’t working. We don’t think this is a path.” And I’ll say, “Okay, let’s spend one more day thinking about it.” Oftentimes, there’ll be some breakthrough that no one saw coming. I don’t know how someone hasn’t made a movie about this. There are just so many stories. I mean, early Starship, back in the Hopper days, it was like…"
2:54

Revel Founder & CEO Scott Morton spent 9 years working at SpaceX / Starship for Elon Musk: Biggest lesson? "Elon Musk is really good at is asking engineers to go further than they otherwise would have." i.e. Push past the first “no.” - Avoid incremental thinking. - Question every requirement & constraint. - Force one more round of thinking. - Breakthroughs often follow discomfort. Ref: Walter Isaacson's Biography on Elon: “1. Question every requirement. Each should come with the name of the person who made it. You should never accept that a requirement came from a department, such as from “the legal department” or “the safety department.” You need to know the name of the real person who made that requirement. Then you should question it, no matter how smart that person is. Requirements from smart people are the most dangerous, because people are less likely to question them. Always do so, even if the requirement came from me. Then make the requirements less dumb. 2. Delete any part or process you can. You may have to add them back later. In fact, if you do not end up adding back at least 10% of them, then you didn’t delete enough. 3. Simplify & optimize. This should come after step two. A common mistake is to simplify and optimize a part or a process that should not exist. 4. Accelerate cycle time. Every process can be speeded up. But only do this after you have followed the first three steps. In the Tesla factory, I mistakenly spent a lot of time accelerating processes that I later realized should have been deleted. 5. Automate. That comes last. The big mistake in Nevada and at Fremont was that I began by trying to automate every step. We should have waited until all the requirements had been questioned, parts and processes deleted, and the bugs were shaken out.” . . . Scott Morton (Scott Morton) Founder & CEO of Revel () "Oh man, I have so many stories. But actually, there’s a good one here. I think what Elon’s really good at is asking engineers to go further than they otherwise would have. One of the most interesting examples was the first orbital flight of Starship. We had this maneuver to separate the booster from the ship. We called it the “twig snap.” It essentially looked like a twig snapping in space, and it was a very inefficient way to do it. For the next flight, he was like, “We’re going to do hot staging,” which is where you literally start the Starship engines while it’s still connected to the booster and just blast off. Coming out of that, we all thought, “Okay, cool. We’re going to do the same exact conceptual operations for the next flight. Of course. We’re just going to go nail it this time, right?” And he was like, “No, we’re going to do hot staging on the next flight.” I was actually sitting outside. I wasn’t in the Elon meeting, but I was outside. I saw everyone walk out, and they were all just like, “Oh my God. How are we going to do this?” That week, screenshots started getting shot around. I’m sure everyone was thinking, “Oh, this is going to be really difficult.” But then, throughout the course of the week, some really awesome ideas started coming up. It started to look more and more feasible. Then it became, “How would you manufacture this? How would this all go together?” They ended up inventing, just out of nowhere, a new stage that would sit between the booster and the ship called the hot stage. It would take the blast, and then it would get ejected on reentry for the booster. It worked first shot. That’s insane. I just remember the vibes at SpaceX were like, “Oh my… how in the hell are we going to go do this?” But I think the big lesson there, and something I’ve pulled forward to Revel, is that when engineers come to you and say, “Hey, we just can’t get this to work. This is not possible,” you push them and say, “Well, why don’t you spend two more days thinking about it? Let’s see what comes up. And if nothing, we’ll think about it then.” Engineers really underestimate their ability to creatively problem-solve and come up with new ideas they otherwise never would have thought of when they’re presenting what they think is possible in the moment. I’ll say, “Okay.” They’ll say, “This just isn’t working. We don’t think this is a path.” And I’ll say, “Okay, let’s spend one more day thinking about it.” Oftentimes, there’ll be some breakthrough that no one saw coming. I don’t know how someone hasn’t made a movie about this. There are just so many stories. I mean, early Starship, back in the Hopper days, it was like…"

Molly O’Shea

90,991 görüntüleme • 6 ay önce

If I was trying to GROW an app or ecomm right now, I wouldn't waste money on influencers or ads. I'd hire creators nobody's heard of and use this strategy that's working right now and generating 100k+ app installs to companies like focustree Influencer with 100k followers: $2,000+ for one post. Gets maybe 30k views. Everyone knows it's an ad. Creator with 500 followers: $900 for an entire month. Posts 30 times. Gets 500k+ views total. Feels more organic. That's $1.80 per thousand views versus $6-12 on Facebook. And it doesn't look like an ad because it isn't one. It's just content. "oH bUt ThaT's NoT PoSsIbLE, GrEG" I agree, this shouldn't work. But it's happening more and more and here's why: *new episode of the pod is live and we give you the playbook* But TikTok's For You Page broke the entire game. The algorithm doesn't care about follower count anymore. It only cares if people watch. IG copied this. YT copied this. Everyone copied this. Now some kid with 300 followers can outperform a verified influencer because their content is better. Not their audience. Their content. Most brands haven't figured this out. They're still paying for follower count like it's 2019. So, the smart play is hiring 10 creators instead of 1. Example: Pay 10 creators $900/month each. That's $9k total. Each posts daily across TikTok, Reels, Shorts. That's 900 pieces of content per month. When one hits, you message the group: "Everyone copy this format." Now 10 creators are using the winning formula with their own spin. The algorithm sees ten different videos, not reposts. One viral format becomes ten viral videos. Those teach you what works. You find the next format. It compounds. How to find creators Search your category on TikTok. You don't want influencers with media kits. You want people already making content about your space for fun. DM them: "Want $900/month to keep doing what you're doing?" They're posting anyway. Now they're getting paid. Run it through Discord or WhatsApp. Share what's working daily. "This hook is crushing." "Try this sound." Track everything. When something explodes, everyone pivots to that format until it stops working. This only works for products that make sense in 10 seconds. Apps with one clear feature. Products under $50. Anything bought on impulse. If you need a sales deck to explain it, this isn't for you. The beauty is what happens beyond direct sales. Someone sees your app on TikTok. They don't buy immediately. But next week they Google "that app from TikTok." Your search traffic spikes. Your app store ranking climbs. The halo effect is massive. Right now this is pure arbitrage. In two years, agencies will package this, prices will 10x, and the window closes. But today you can hire a creator army for what one influencer post costs. You can test more in a week than most brands test in a year. You're building a content machine. All algortihms care about nowadays is if people stop scrolling. Find creators who make people stop scrolling. Pay them to never stop posting. Share what works. Scale what hits. People charge $10k for this sort of info. We give it away for free on The Startup Ideas Podcast (SIP) 🧃 2x week. Thanks to for jumping on and sharing. We could keep this to ourselves but where is the fun in that? Fun is seeing you build a bootstrapped app to millions of users through this strategy And sending me a dm And saying "thanks for the tip, professor g" No worries, my friend No worries.
27:37

If I was trying to GROW an app or ecomm right now, I wouldn't waste money on influencers or ads. I'd hire creators nobody's heard of and use this strategy that's working right now and generating 100k+ app installs to companies like focustree Influencer with 100k followers: $2,000+ for one post. Gets maybe 30k views. Everyone knows it's an ad. Creator with 500 followers: $900 for an entire month. Posts 30 times. Gets 500k+ views total. Feels more organic. That's $1.80 per thousand views versus $6-12 on Facebook. And it doesn't look like an ad because it isn't one. It's just content. "oH bUt ThaT's NoT PoSsIbLE, GrEG" I agree, this shouldn't work. But it's happening more and more and here's why: *new episode of the pod is live and we give you the playbook* But TikTok's For You Page broke the entire game. The algorithm doesn't care about follower count anymore. It only cares if people watch. IG copied this. YT copied this. Everyone copied this. Now some kid with 300 followers can outperform a verified influencer because their content is better. Not their audience. Their content. Most brands haven't figured this out. They're still paying for follower count like it's 2019. So, the smart play is hiring 10 creators instead of 1. Example: Pay 10 creators $900/month each. That's $9k total. Each posts daily across TikTok, Reels, Shorts. That's 900 pieces of content per month. When one hits, you message the group: "Everyone copy this format." Now 10 creators are using the winning formula with their own spin. The algorithm sees ten different videos, not reposts. One viral format becomes ten viral videos. Those teach you what works. You find the next format. It compounds. How to find creators Search your category on TikTok. You don't want influencers with media kits. You want people already making content about your space for fun. DM them: "Want $900/month to keep doing what you're doing?" They're posting anyway. Now they're getting paid. Run it through Discord or WhatsApp. Share what's working daily. "This hook is crushing." "Try this sound." Track everything. When something explodes, everyone pivots to that format until it stops working. This only works for products that make sense in 10 seconds. Apps with one clear feature. Products under $50. Anything bought on impulse. If you need a sales deck to explain it, this isn't for you. The beauty is what happens beyond direct sales. Someone sees your app on TikTok. They don't buy immediately. But next week they Google "that app from TikTok." Your search traffic spikes. Your app store ranking climbs. The halo effect is massive. Right now this is pure arbitrage. In two years, agencies will package this, prices will 10x, and the window closes. But today you can hire a creator army for what one influencer post costs. You can test more in a week than most brands test in a year. You're building a content machine. All algortihms care about nowadays is if people stop scrolling. Find creators who make people stop scrolling. Pay them to never stop posting. Share what works. Scale what hits. People charge $10k for this sort of info. We give it away for free on The Startup Ideas Podcast (SIP) 🧃 2x week. Thanks to for jumping on and sharing. We could keep this to ourselves but where is the fun in that? Fun is seeing you build a bootstrapped app to millions of users through this strategy And sending me a dm And saying "thanks for the tip, professor g" No worries, my friend No worries.

GREG ISENBERG

100,585 görüntüleme • 1 yıl önce

New episode: "How Elon Works" This episode covers the insanely valuable company-building principles of Elon Musk A few notes from the episode: 1. The mission comes first. 2. Retreat is not an option. 3. A maniacal sense of urgency is our operating principle. 4. Product design should be driven by engineers. 5. You should not separate engineering from product design. 6. Having separate design and production departments is bullshit. Keep everything together and feedback immediate. 7. The leader should be on the front lines. You should be a battlefield general. 8. "If they see the general out on the battlefield, the troops are going to be motivated. Wherever Napoleon was, that's where his armies would do best." 9. Apply The Algorithm constantly. (1) Question every requirement. (2) Delete any part of the process you can. (3) Simplify and optimize. (4) Accelerate cycle time. (5) Automate. 10. Repetition is persuasive. "I became a broken record on the algorithm. I think it's helpful to say it to an annoying degree." 11. You should go ultra-hardcore on deletion and simplification. 12. Camaraderie is dangerous. It makes it hard for people to challenge each other’s work. (Refer to point #1) 13. Never ask your troops to do something you wouldn’t do. 14. Hire for attitude. Skills can be taught. Attitude changes require a brain transplant. 15. Good attitude = A desire to work maniacally hard. 16. The only rules are the ones dictated by the laws of physics. Everything else is a recommendation. 17. Keep your entire company committed to a common goal. 18. If things aren’t going well, throw away the existing design, start from first principles, question every requirement based on fundamental physics. 19. Find the limit. You want to delete as much as possible and you can’t do that unless you find the limit. 20. If you aren’t adding back at least 10% of the things you deleted, then you didn’t delete enough. 21. Maintain control. Avoid joint ventures. Eliminate middlemen. 22. Have a relentless dedication to questioning every requirement. 23. No work about work, just work. 24. Go to the problem. Get on the plane. Fly to the source. Go to the exact location in the factory. Go to the problem and stay there until it's resolved. 25. The best part is no part. 26. Be wired for war. 27. Do not fear losing. It hurts the first 50 times but then you’ll be able to play with less emotion. You will take more risks. 28. Stay heads down focused on doing useful things for civilization. 29. When something is important and has to be done quickly, have meetings every 24 hours to run the algorithm and check on the previous days progress. You'll be shocked at how fast this speeds things up. 30. Life needs to be interesting and edgy. 31. Delete, delete, delete, delete. There are 100 more ideas in the episode. I hope you listen to it. 30 years of Elon’s career + 60 hours of reading and research and me just absolutely ripping through idea after idea at 2x speed for 90 minutes. It will be hard to find a better use of time.
1:33:02

New episode: "How Elon Works" This episode covers the insanely valuable company-building principles of Elon Musk A few notes from the episode: 1. The mission comes first. 2. Retreat is not an option. 3. A maniacal sense of urgency is our operating principle. 4. Product design should be driven by engineers. 5. You should not separate engineering from product design. 6. Having separate design and production departments is bullshit. Keep everything together and feedback immediate. 7. The leader should be on the front lines. You should be a battlefield general. 8. "If they see the general out on the battlefield, the troops are going to be motivated. Wherever Napoleon was, that's where his armies would do best." 9. Apply The Algorithm constantly. (1) Question every requirement. (2) Delete any part of the process you can. (3) Simplify and optimize. (4) Accelerate cycle time. (5) Automate. 10. Repetition is persuasive. "I became a broken record on the algorithm. I think it's helpful to say it to an annoying degree." 11. You should go ultra-hardcore on deletion and simplification. 12. Camaraderie is dangerous. It makes it hard for people to challenge each other’s work. (Refer to point #1) 13. Never ask your troops to do something you wouldn’t do. 14. Hire for attitude. Skills can be taught. Attitude changes require a brain transplant. 15. Good attitude = A desire to work maniacally hard. 16. The only rules are the ones dictated by the laws of physics. Everything else is a recommendation. 17. Keep your entire company committed to a common goal. 18. If things aren’t going well, throw away the existing design, start from first principles, question every requirement based on fundamental physics. 19. Find the limit. You want to delete as much as possible and you can’t do that unless you find the limit. 20. If you aren’t adding back at least 10% of the things you deleted, then you didn’t delete enough. 21. Maintain control. Avoid joint ventures. Eliminate middlemen. 22. Have a relentless dedication to questioning every requirement. 23. No work about work, just work. 24. Go to the problem. Get on the plane. Fly to the source. Go to the exact location in the factory. Go to the problem and stay there until it's resolved. 25. The best part is no part. 26. Be wired for war. 27. Do not fear losing. It hurts the first 50 times but then you’ll be able to play with less emotion. You will take more risks. 28. Stay heads down focused on doing useful things for civilization. 29. When something is important and has to be done quickly, have meetings every 24 hours to run the algorithm and check on the previous days progress. You'll be shocked at how fast this speeds things up. 30. Life needs to be interesting and edgy. 31. Delete, delete, delete, delete. There are 100 more ideas in the episode. I hope you listen to it. 30 years of Elon’s career + 60 hours of reading and research and me just absolutely ripping through idea after idea at 2x speed for 90 minutes. It will be hard to find a better use of time.

David Senra

3,752,564 görüntüleme • 1 yıl önce