Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Anthropic recently cut Claude Code’s system prompt by 80%. Thariq explains why: “As the models have gotten smarter, they need less direction, fewer constraints, and fewer examples. The examples are constraining it because now it’s like, ‘Oh, you want things like this example.’ If you remove the examples, it... show more

Peter Yang

245,962 subscribers

316,685 views • 4 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

“We’ve got /loop, /goal, and workflows. They all get the agent to run for long periods of time.” Here’s my new episode with Thariq from the Claude Code team, where he shared how he plans, builds, and runs loops with Claude Code: → How /loop, /goal, and workflows work differently → Live demo: Editing launch videos with Claude → Using HTML artifacts to plan and learn Some quotes from Thariq: “We cut Claude Code’s system prompt by 80%. As models have gotten smarter, they need less direction, fewer constraints, and fewer examples.” “Planning is an iterative process of exploring, investigating, and finding out what you don’t know.” “One failure mode I see is that people glaze over AI’s plans. You want to make sure it’s something you read.” I've been wanting to interview Thariq for a long time and I learned so much from this epsiode. 📌 Watch now: Thanks to our sponsors: Riverside: All-in-one AI studio for podcasts and video Wispr Flow: 4x faster than typing with your voice

“We’ve got /loop, /goal, and workflows. They all get the agent to run for long periods of time.” Here’s my new episode with Thariq from the Claude Code team, where he shared how he plans, builds, and runs loops with Claude Code: → How /loop, /goal, and workflows work differently → Live demo: Editing launch videos with Claude → Using HTML artifacts to plan and learn Some quotes from Thariq: “We cut Claude Code’s system prompt by 80%. As models have gotten smarter, they need less direction, fewer constraints, and fewer examples.” “Planning is an iterative process of exploring, investigating, and finding out what you don’t know.” “One failure mode I see is that people glaze over AI’s plans. You want to make sure it’s something you read.” I've been wanting to interview Thariq for a long time and I learned so much from this epsiode. 📌 Watch now: Thanks to our sponsors: Riverside: All-in-one AI studio for podcasts and video Wispr Flow: 4x faster than typing with your voice

Peter Yang

180,909 views • 4 days ago

Anthropic team: "Most people are prompting Claude wrong" They dropped a 24-minute workshop on how Claude prompts are actually built Free From the people who built the model There are 6 elements in a real Claude prompt Most people use 1 That is why their outputs feel generic Better wording is not enough Claude rewards structure, context, examples, constraints, and feedback I watched it twice Then built a Claude Skill that applies all 6 automatically You write normally The skill structures the prompt before Claude sees it Bookmark and watch this Then save the setup below

Anthropic team: "Most people are prompting Claude wrong" They dropped a 24-minute workshop on how Claude prompts are actually built Free From the people who built the model There are 6 elements in a real Claude prompt Most people use 1 That is why their outputs feel generic Better wording is not enough Claude rewards structure, context, examples, constraints, and feedback I watched it twice Then built a Claude Skill that applies all 6 automatically You write normally The skill structures the prompt before Claude sees it Bookmark and watch this Then save the setup below

rari

15,655 views • 20 days ago

If you want to get hired at an AI company right now, this is what they need to say about you when you leave the room, directly from jack and Roelof Botha Watch the full episode here:

If you want to get hired at an AI company right now, this is what they need to say about you when you leave the room, directly from jack and Roelof Botha Watch the full episode here:

Brian Halligan

25,932 views • 3 months ago

"We need the remaining nations of Esav and Ishmael to fight it out over Israel" "We need the Christians and the Muslims to fight it out over Israel. They want us to destroy each other" "How many examples do we have to show that this is what, like all the rabbis are saying this"

"We need the remaining nations of Esav and Ishmael to fight it out over Israel" "We need the Christians and the Muslims to fight it out over Israel. They want us to destroy each other" "How many examples do we have to show that this is what, like all the rabbis are saying this"

Seethroughitall

54,315 views • 1 year ago

Anthropic engineer: "Fable is one of those models you’ll just remember - like Sonnet 3.5, Opus 4, Opus 4.5. We just removed 80% of Claude Code’s system prompt. A new class of models wants a smaller prompt." in 20-minute session, an Anthropic core engineer reveals the capabilities of Fable. Watch it now, then read how to use this frontier model in the article below.

Anthropic engineer: "Fable is one of those models you’ll just remember - like Sonnet 3.5, Opus 4, Opus 4.5. We just removed 80% of Claude Code’s system prompt. A new class of models wants a smaller prompt." in 20-minute session, an Anthropic core engineer reveals the capabilities of Fable. Watch it now, then read how to use this frontier model in the article below.

Movez

549,656 views • 22 days ago

.Anish Acharya says the future of AI isn’t one model to rule them all—and explains why platforms that integrate multiple models will benefit the most: "I think we're going to need and rely on all of the models." "It's sort of like if you have a team of people... if you have five people, they could all do a basic set of things pretty capably." "But then they all have their specializations. Maybe one of them is really good at closing a customer who doesn't want to sign the deal, and one of them is really good at culture and getting the best out of the team." "There are some areas in which they are going to build apps, and that will be a threat to app companies. But there are many areas in which app companies are advantaged. Cursor and Krea are great examples of this—products where you benefit from being multi-model." "When you actually use a creative tool, you don't want to just use Nano Banana, you want to have access to OpenAI, Nano Banana, Kling—all of them—Qwen, you name it. So using a single interface to access all the models is powerful." Anish Acharya on BILLIONS with Guillaume Moubeche

.Anish Acharya says the future of AI isn’t one model to rule them all—and explains why platforms that integrate multiple models will benefit the most: "I think we're going to need and rely on all of the models." "It's sort of like if you have a team of people... if you have five people, they could all do a basic set of things pretty capably." "But then they all have their specializations. Maybe one of them is really good at closing a customer who doesn't want to sign the deal, and one of them is really good at culture and getting the best out of the team." "There are some areas in which they are going to build apps, and that will be a threat to app companies. But there are many areas in which app companies are advantaged. Cursor and Krea are great examples of this—products where you benefit from being multi-model." "When you actually use a creative tool, you don't want to just use Nano Banana, you want to have access to OpenAI, Nano Banana, Kling—all of them—Qwen, you name it. So using a single interface to access all the models is powerful." Anish Acharya on BILLIONS with Guillaume Moubeche

a16z

33,175 views • 4 months ago

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,510 views • 3 years ago

Do you have a visualiser in your cupboard? Plug it into your computer and see how you can bring the teaching slides to life through live modelling! 🎬 By using the visualiser, you can model your thinking aloud and children can build alongside you. It also gives you the flexibility to model as many examples as you may need! 🟡🔴

Do you have a visualiser in your cupboard? Plug it into your computer and see how you can bring the teaching slides to life through live modelling! 🎬 By using the visualiser, you can model your thinking aloud and children can build alongside you. It also gives you the flexibility to model as many examples as you may need! 🟡🔴

White Rose Education

20,955 views • 1 year ago

Imagine an AI application that can type anywhere you can and use the full context of what's on your screen. This is the application we all deserve (at least if you have macOS.) Check out Omnipilot. It's an app that works with every other macOS application and uses Claude Sonet 3.5 in the background—it also supports Gemini and GPT-4o. Here is the idea: You can use the tool to ask questions about anything on your screen. Or you can use it to autocomplete the text you are typing. You don't need to copy and paste anymore or waste your time providing context to a model. It sees what you see. It works right where you are. That's pretty cool. Here are a couple of cool examples: • Use it to reply to an email • Use it in the terminal to autocomplete a command • Use it to finish a document • Use to send a message on Slack AI at the system level is bonkers. You can read a ton more on their Product Hunt launch page: Thanks to the Omnipilot team for collaborating with me on this post!

Imagine an AI application that can type anywhere you can and use the full context of what's on your screen. This is the application we all deserve (at least if you have macOS.) Check out Omnipilot. It's an app that works with every other macOS application and uses Claude Sonet 3.5 in the background—it also supports Gemini and GPT-4o. Here is the idea: You can use the tool to ask questions about anything on your screen. Or you can use it to autocomplete the text you are typing. You don't need to copy and paste anymore or waste your time providing context to a model. It sees what you see. It works right where you are. That's pretty cool. Here are a couple of cool examples: • Use it to reply to an email • Use it in the terminal to autocomplete a command • Use it to finish a document • Use to send a message on Slack AI at the system level is bonkers. You can read a ton more on their Product Hunt launch page: Thanks to the Omnipilot team for collaborating with me on this post!

Santiago

72,306 views • 2 years ago

"More cult leaders, less Mr. Beast." sam lessin 🏴‍☠️ explains why the next era of the creator economy is about depth over distribution: "What you really want is your true believers. You need a core audience that is like, this is the person that I choose to trust in life, and I have a reason for it."

"More cult leaders, less Mr. Beast." sam lessin 🏴‍☠️ explains why the next era of the creator economy is about depth over distribution: "What you really want is your true believers. You need a core audience that is like, this is the person that I choose to trust in life, and I have a reason for it."

The Information

19,969 views • 6 months ago

Is Traditional Software Engineering Dead? “Does this mean that traditional software engineering is dead? Absolutely not. Software engineers—even the ones who are not necessarily tuning or training AI models—these are now among the most leveraged people on earth. Sure, the guys who are training and tuning models are even more leveraged because they’re building the tool set that software engineers are using. But software engineers still have two massive advantages on you. First, they think in code, so they actually know what’s going on underneath. And all abstractions are leaky. So when you have a computer programming for you—when you have Claude Code or equivalent programming for you—it’s going to make mistakes. It’s going to have bugs. It’s going to have suboptimal architecture. So it’s not going to be quite right. And someone who understands what’s going on underneath will be able to plug the leaks as they occur. So if you want to build a well-architected application, if you want to be able to even specify a well-architected application, if you want to be able to make it run at high performance, if you want it to do its best, if you want to catch the bugs early, then you’re going to want to have a software engineering background. The traditional software engineer is going to be able to use these tools much better. And there are still many kinds of problems in software engineering that are out of scope for these AI programs today. The easiest way to think about those is problems that are outside of their data distribution. For example, if they need to do a binary sort or reverse a linked list, they’ve seen countless examples of that, so they’re extremely good at it. But when you start getting out of their domain—where you have to write very high-performance code, when you’re running on architectures that are novel or brand new, when you’re actually creating new things or solving new problems, then you still need to get in there and hand code it. At least until either there are so many of those examples that new models can be trained on them, or until these models can sufficiently reason at even higher levels of abstraction and crack it on their own… And remember: there is no demand for average. The average app—nobody wants it, at least as long as it’s not filling some niche that is filled by a superior app. The app that is better will win essentially a hundred percent of the market. Maybe there’s some small percentage that will bleed off to the second-best app because it does some little niche feature better than the main app, or it’s cheaper, or something of the sort. But generally speaking, people only want the best of anything. So the bad news is there’s no point in being number two or number three—like in the famous Glengarry Glen Ross scene where Alec Baldwin says, “First place gets a Cadillac Eldorado, second place gets a set of steak knives, and third place you’re fired.” That’s absolutely true in these winner-take-all markets. That’s the bad news: You have to be the best at something if you want to win. However, the set of things you can be best at is infinite. You can always find some niche that is perfect for you, and you can be the best at that thing. This goes back to an old tweet of mine where I said, “Become the best in the world at what you do. Keep redefining what you do until this is true.” And I think that still applies in this age of AI.”

Naval

850,600 views • 4 months ago

Steven Pinker is Harvard's most famous psychology professor, the author of nine books, and one of Time Magazine's 100 most influential people. Some highlights from our interview: 1. The curse of knowledge is the biggest threat to clear writing. 2. The easiest way to fight this curse of knowledge is to show drafts of your writing to people outside your field. 3. It can be harder to write about a topic you’re an expert in because it’s so easy to forget what it's like to not know something, which makes you overestimate what the reader knows. 4. Shakespeare said: "Brevity is the soul of wit." The point is that saying something in fewer words will almost always make it better because it requires less cognitive load for the reader to understand. 5. Ok, let's try again: Saying something in fewer words will almost always make it better. 6. Ok, one more time: Remove needless words. 7. One reason why writing is harder than speaking is there's no real-time feedback. You have to imagine the audience's reaction. 7. The best thing you can say about how LLMs write is that the sentence structure is sound. But the downside is how generic and banal the outputs are. 8. 18th and 19th century writing is more vivid because the abstractions that modern writers use hadn't been invented yet. Calling somebody "pathologically aggressive" isn’t nearly as vivid as saying: "They grabbed me by the throat." 9. Generalizations without examples are useless, and examples without generalizations are pointless. You need to marry them both. Generalizations show the big picture. Examples make them concrete. 10. The more vivid a piece of writing, the more people can form a mental image of what you’re saying. Avoid abstractions: frameworks, paradigms, concepts. All those things. Get concrete, so people can see what you’re actually talking about. For example, don’t talk about a “stimulus that awakened your senses” when you can say: “I got excited because I saw a cute bunny rabbit.” 11. Academic writing should be clear. I mean… if the taxpayers are funding most of the research, shouldn’t they be able to understand it?!? I've shared the full conversation with Steven Pinker below. If you'd rather watch on YouTube or listen on Apple or Spotify, check out the reply tweets.

Steven Pinker is Harvard's most famous psychology professor, the author of nine books, and one of Time Magazine's 100 most influential people. Some highlights from our interview: 1. The curse of knowledge is the biggest threat to clear writing. 2. The easiest way to fight this curse of knowledge is to show drafts of your writing to people outside your field. 3. It can be harder to write about a topic you’re an expert in because it’s so easy to forget what it's like to not know something, which makes you overestimate what the reader knows. 4. Shakespeare said: "Brevity is the soul of wit." The point is that saying something in fewer words will almost always make it better because it requires less cognitive load for the reader to understand. 5. Ok, let's try again: Saying something in fewer words will almost always make it better. 6. Ok, one more time: Remove needless words. 7. One reason why writing is harder than speaking is there's no real-time feedback. You have to imagine the audience's reaction. 7. The best thing you can say about how LLMs write is that the sentence structure is sound. But the downside is how generic and banal the outputs are. 8. 18th and 19th century writing is more vivid because the abstractions that modern writers use hadn't been invented yet. Calling somebody "pathologically aggressive" isn’t nearly as vivid as saying: "They grabbed me by the throat." 9. Generalizations without examples are useless, and examples without generalizations are pointless. You need to marry them both. Generalizations show the big picture. Examples make them concrete. 10. The more vivid a piece of writing, the more people can form a mental image of what you’re saying. Avoid abstractions: frameworks, paradigms, concepts. All those things. Get concrete, so people can see what you’re actually talking about. For example, don’t talk about a “stimulus that awakened your senses” when you can say: “I got excited because I saw a cute bunny rabbit.” 11. Academic writing should be clear. I mean… if the taxpayers are funding most of the research, shouldn’t they be able to understand it?!? I've shared the full conversation with Steven Pinker below. If you'd rather watch on YouTube or listen on Apple or Spotify, check out the reply tweets.

David Perell

107,348 views • 1 year ago

you don’t need to love trading you just need to know how to use it to get the life you want people treat trading like it’s a personality like you have to obsess over it or it won’t work but trading is a tool like a microwave you don’t need to love it you need it to work fast and be consistent my students don’t wake up dreaming about candlesticks they wake up to freedom because the system does the heavy lifting comment SYSTEM and I’ll send you the exact framework I use to trade 1hr a day and live free trading isn’t a lifestyle it funds the lifestyle

you don’t need to love trading you just need to know how to use it to get the life you want people treat trading like it’s a personality like you have to obsess over it or it won’t work but trading is a tool like a microwave you don’t need to love it you need it to work fast and be consistent my students don’t wake up dreaming about candlesticks they wake up to freedom because the system does the heavy lifting comment SYSTEM and I’ll send you the exact framework I use to trade 1hr a day and live free trading isn’t a lifestyle it funds the lifestyle

Run It Up $$$

15,108 views • 6 months ago

NAVAL: ELON BUILDS THINGS THAT ARE TECHNICALLY HARD BUT OBVIOUSLY USEFUL “Like a lot of us, I'm inspired by Elon, and all the incredible work he's done. So, I don't want to build things that are easy. I want to build things that are hard and interesting. I want to take on more technical risk and less market risk. This is the classic VC learning: You want to build something that, if people get it, if you can deliver it, you know people will want it. It's just hard to build. As opposed to things that you want to build, and you don't know if people will want it.” Source: All-In Podcast, February 14, 2025

NAVAL: ELON BUILDS THINGS THAT ARE TECHNICALLY HARD BUT OBVIOUSLY USEFUL “Like a lot of us, I'm inspired by Elon, and all the incredible work he's done. So, I don't want to build things that are easy. I want to build things that are hard and interesting. I want to take on more technical risk and less market risk. This is the classic VC learning: You want to build something that, if people get it, if you can deliver it, you know people will want it. It's just hard to build. As opposed to things that you want to build, and you don't know if people will want it.” Source: All-In Podcast, February 14, 2025

Mario Nawfal

135,417 views • 1 year ago

We asked rahul about the global reach of ChatGPT and the emphasis on personality in AI models. "When you want to get to the one to like the remaining 90% of the users, do you want a model that thinks for longer? You want more personality?" "They definitely leaned in on personality, which I think is interesting." "It's kind of different than a (social media) feed in some ways because you have this person you talk to. It's like a relationship and then it just switches up on how it talks to you."

We asked rahul about the global reach of ChatGPT and the emphasis on personality in AI models. "When you want to get to the one to like the remaining 90% of the users, do you want a model that thinks for longer? You want more personality?" "They definitely leaned in on personality, which I think is interesting." "It's kind of different than a (social media) feed in some ways because you have this person you talk to. It's like a relationship and then it just switches up on how it talks to you."

TBPN

89,226 views • 11 months ago

🚨 GREG BROCKMAN JUST EXPLAINED THE NEXT LEAP WITH SPUD (GPT 5.5) Greg Brockman: "I think of Spud as a new base, as a new pre-train... I'd say it's like we have maybe two years worth of research that is coming to fruition in this model." Greg says: "There's this thing called 'big model smell'... when these models are just actually much smarter, much more capable, that they bend to you much more, and you feel it." Here is exactly what we are getting with the upcoming GPT 5.5 rollout: • "Big Model Smell": A massive qualitative shift. The models stop being rigid and start intuitively bending to what you actually want them to do. • Unlocking New Abilities: It can just do things it wasn’t able to before. The frustrating moments where the AI "doesn't quite get it" and needs you to over-explain are going away. • Longer Time Horizons: The ceiling is being completely raised. The new models will be able to autonomously solve complex, open-ended problems over much longer periods of time. • A New Pre-Train Base: This is not an incremental fine-tune. Spud is a completely new foundation built to accelerate the entire economy.

🚨 GREG BROCKMAN JUST EXPLAINED THE NEXT LEAP WITH SPUD (GPT 5.5) Greg Brockman: "I think of Spud as a new base, as a new pre-train... I'd say it's like we have maybe two years worth of research that is coming to fruition in this model." Greg says: "There's this thing called 'big model smell'... when these models are just actually much smarter, much more capable, that they bend to you much more, and you feel it." Here is exactly what we are getting with the upcoming GPT 5.5 rollout: • "Big Model Smell": A massive qualitative shift. The models stop being rigid and start intuitively bending to what you actually want them to do. • Unlocking New Abilities: It can just do things it wasn’t able to before. The frustrating moments where the AI "doesn't quite get it" and needs you to over-explain are going away. • Longer Time Horizons: The ceiling is being completely raised. The new models will be able to autonomously solve complex, open-ended problems over much longer periods of time. • A New Pre-Train Base: This is not an incremental fine-tune. Spud is a completely new foundation built to accelerate the entire economy.

Chris

201,638 views • 3 months ago

"So now that the government is back open, this should be a lesson, or a warning." "You should probably get your sh*t together." "By now 2 things should be clear to you. First, the government doesn't care about your dependency to feed your children, and that the Republicans want to get away from government assistance altogether." BASED. The more you rely on the government, the less free you are. It is as simple as that.

"So now that the government is back open, this should be a lesson, or a warning." "You should probably get your sh*t together." "By now 2 things should be clear to you. First, the government doesn't care about your dependency to feed your children, and that the Republicans want to get away from government assistance altogether." BASED. The more you rely on the government, the less free you are. It is as simple as that.

AmericanPapaBear™

20,831 views • 8 months ago

It used to be that the Left just wanted us to have fewer guns. Now they want us to have fewer goals. They think we should have a smaller house, a smaller family, and less money in the diminished America today under Joe Biden. Under President Trump, we could build more, grow more, and have more. That’s why this is Donald Trump’s party, and I’m honored to be a Donald Trump Republican!

It used to be that the Left just wanted us to have fewer guns. Now they want us to have fewer goals. They think we should have a smaller house, a smaller family, and less money in the diminished America today under Joe Biden. Under President Trump, we could build more, grow more, and have more. That’s why this is Donald Trump’s party, and I’m honored to be a Donald Trump Republican!

Former Congressman Matt Gaetz

114,039 views • 2 years ago

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 views • 4 months ago

KEILAR: The Heritage Foundation database of confirmed fraud cases shows fewer than 100 examples of noncitizens improperly casting ballots between 2000 and 2025 REP. JOHN ROSE: Well if it's not a problem, then it shouldn't be a problem to pass it KEILAR: I'm explaining to you why Republicans are opposed to it. They say you are creating a problem with the bill

KEILAR: The Heritage Foundation database of confirmed fraud cases shows fewer than 100 examples of noncitizens improperly casting ballots between 2000 and 2025 REP. JOHN ROSE: Well if it's not a problem, then it shouldn't be a problem to pass it KEILAR: I'm explaining to you why Republicans are opposed to it. They say you are creating a problem with the bill

Aaron Rupar

129,520 views • 29 days ago