正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

“There aren’t many high-quality, high-performance Layer 1s — but one in particular stood out once we dug into the details,” says Richard G Brown, reflecting on why the team selected Solana. A parallelised execution model, a safer programming language, and an architectural approach built to remove familiar bottlenecks shifted... show more

R3

59,980 subscribers

22,570 次观看 • 7 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

“It’s not sufficient to bring the asset on-chain. You must transform it into a form that the on-chain investor is happy to embrace.” As Richard G Brown explains, there is already a large and growing pool of capital on-chain, held in stablecoins, crypto treasuries, and by investors who have made money in crypto. This capital runs into the hundreds of billions globally, and it’s increasingly looking for real yield and institutional-grade assets. These allocators don’t want to move back into the old world of legacy custodians or traditional settlement processes. Their liquidity needs, access requirements, investment sizes, and jurisdictions differ from traditional buyers - and they expect assets to meet them where they already are: on-chain. That’s why the challenge isn’t simply tokenising an asset. It’s reshaping it so on-chain investors can use it, trade it, and exit it in ways consistent with their market structure. A powerful insight from Richard Gendal Brown’s conversation with Future of Finance (FOF), and a clear signal of where institutional digital assets are heading. Watch the full podcast here: Want to learn more about what R3 is bringing to Solana? Catch Richard on stage at SolanaConf Breakpoint, 11-13 December.

“It’s not sufficient to bring the asset on-chain. You must transform it into a form that the on-chain investor is happy to embrace.” As Richard G Brown explains, there is already a large and growing pool of capital on-chain, held in stablecoins, crypto treasuries, and by investors who have made money in crypto. This capital runs into the hundreds of billions globally, and it’s increasingly looking for real yield and institutional-grade assets. These allocators don’t want to move back into the old world of legacy custodians or traditional settlement processes. Their liquidity needs, access requirements, investment sizes, and jurisdictions differ from traditional buyers - and they expect assets to meet them where they already are: on-chain. That’s why the challenge isn’t simply tokenising an asset. It’s reshaping it so on-chain investors can use it, trade it, and exit it in ways consistent with their market structure. A powerful insight from Richard Gendal Brown’s conversation with Future of Finance (FOF), and a clear signal of where institutional digital assets are heading. Watch the full podcast here: Want to learn more about what R3 is bringing to Solana? Catch Richard on stage at SolanaConf Breakpoint, 11-13 December.

R3

21,554 次观看 • 7 个月前

.Secretary of War Pete Hegseth “What an honor it is being here today at Starbase Texas with Elon Musk and the SpaceX team. there is nothing like this in America. There is nothing like this in the WORLD. What you have built—and what you will build here is a testament to the strength of American ingenuity and invention…"

.Secretary of War Pete Hegseth “What an honor it is being here today at Starbase Texas with Elon Musk and the SpaceX team. there is nothing like this in America. There is nothing like this in the WORLD. What you have built—and what you will build here is a testament to the strength of American ingenuity and invention…"

DOW Rapid Response

447,295 次观看 • 6 个月前

Secretary of War Pete Hegseth: “What an honor it’s being here today at Starbase Texas with Elon Musk and the SpaceX team. There is nothing like this in the world… What you have built and what you will build here is a testament to the strength of American ingenuity and invention”

Secretary of War Pete Hegseth: “What an honor it’s being here today at Starbase Texas with Elon Musk and the SpaceX team. There is nothing like this in the world… What you have built and what you will build here is a testament to the strength of American ingenuity and invention”

America

93,547 次观看 • 6 个月前

Reporter: We have learned more about what happened in the room when Trump learned of the Supreme Court decision. He became enraged, calling the decision a disgrace, and started attacking the courts, at one point saying, 'these effing courts,' but using the actual language there. This could not be a bigger loss for Trump.

Reporter: We have learned more about what happened in the room when Trump learned of the Supreme Court decision. He became enraged, calling the decision a disgrace, and started attacking the courts, at one point saying, 'these effing courts,' but using the actual language there. This could not be a bigger loss for Trump.

FactPost

96,379 次观看 • 5 个月前

Sam Altman, OpenAI CEO: "with an affordable amount of spend on tokens, you can do what a 100-person incredibly great engineering team would do as a startup." in this 40-minute Stanford talk, he breaks down the exact shift that lets a solo founder out-build a 100-person team. free. straight from the Stanford stage. worth more than a $2,000 startup accelerator. so i stopped arguing and built one. local agents. local tool. nothing leaving my laptop. an Obsidian clone, a knowledge graph, 13 agents a full second brain. solo. what a whole team would've shipped. minus the team. minus the cloud. here's the shift he breaks down and what i found building on it: - why tokens replaced headcount - the "one-person frontier lab" model ; your second brain is the lab - the inference layer every founder is sleeping on - why hiring 100 engineers is now the expensive way to build the 100-person team didn't get cheaper. it became one person, a second brain, and a swarm of agents. bookmark this. the full build is in the article below ⬇️

Sam Altman, OpenAI CEO: "with an affordable amount of spend on tokens, you can do what a 100-person incredibly great engineering team would do as a startup." in this 40-minute Stanford talk, he breaks down the exact shift that lets a solo founder out-build a 100-person team. free. straight from the Stanford stage. worth more than a $2,000 startup accelerator. so i stopped arguing and built one. local agents. local tool. nothing leaving my laptop. an Obsidian clone, a knowledge graph, 13 agents a full second brain. solo. what a whole team would've shipped. minus the team. minus the cloud. here's the shift he breaks down and what i found building on it: - why tokens replaced headcount - the "one-person frontier lab" model ; your second brain is the lab - the inference layer every founder is sleeping on - why hiring 100 engineers is now the expensive way to build the 100-person team didn't get cheaper. it became one person, a second brain, and a swarm of agents. bookmark this. the full build is in the article below ⬇️

Avid

65,042 次观看 • 1 个月前

Just another one of the true stories that refutes the false history that we were docile men “What an amazing story, told by the straight shooter himself; Walter Brown tells the story of a particular payday in the Greenville levee camp when he was compelled to demand the pay that was owed to him. If you watch the full story, it was his 12 year old wife who compelled him to demand his due payment, and he was 13, not 12 at the time of the confrontation with Mr Brown. Shot by Alan Lomax, John Bishop, and Worth tory Long on the levee in Greenville, Mississippi, August 22, 1978. This is an edited version of this story told by Walter Brown. For the full story and many more like it head to Alan Lomax Film Collection on YT.”-Mississippi Vibes

Just another one of the true stories that refutes the false history that we were docile men “What an amazing story, told by the straight shooter himself; Walter Brown tells the story of a particular payday in the Greenville levee camp when he was compelled to demand the pay that was owed to him. If you watch the full story, it was his 12 year old wife who compelled him to demand his due payment, and he was 13, not 12 at the time of the confrontation with Mr Brown. Shot by Alan Lomax, John Bishop, and Worth tory Long on the levee in Greenville, Mississippi, August 22, 1978. This is an edited version of this story told by Walter Brown. For the full story and many more like it head to Alan Lomax Film Collection on YT.”-Mississippi Vibes

GEN

49,439 次观看 • 6 个月前

There haven’t been many more true positionless players in College Basketball this season than 6’4 Saint Louis Senior Dion Brown. Brown has been one of the most impressive players in the A10 this season averaging 13/7/2 while shooting 66% from the field in only 23 MPG. Despite only being 6’4 Brown provides amazing versatility and has played the 1-5 for Saint Louis this season at a high level. Brown is one of the best finisher and rebounders in the country at 6’4 and uses his mix of strength and high motor to fight for rebounds on both ends and finish through contact on a drive, a cut, or in the post. Brown is shooting an impressive 78% at the rim which is 7% higher than the next 6’6 or smaller player with 50 attempts at the rim. Brown is also a very skilled passer, and uses his ability to play anywhere on the court to find his teammates as a ball handler or as an off ball player. On the defensive end Brown has been one of the most versatile and effective defenders in the A10 as well. Brown and Arrinten Page have been the only players in the country this season to shoot 75% at the rim on at least 50 attempts, have an AST% of 15 and make 5 threes or more. Brown’s mix of finishing, rebounding, versatility, motor, defense, and passing at 6’4 make him an extremely unique and valuable player and he’s been one of the most underrated players in the country.

There haven’t been many more true positionless players in College Basketball this season than 6’4 Saint Louis Senior Dion Brown. Brown has been one of the most impressive players in the A10 this season averaging 13/7/2 while shooting 66% from the field in only 23 MPG. Despite only being 6’4 Brown provides amazing versatility and has played the 1-5 for Saint Louis this season at a high level. Brown is one of the best finisher and rebounders in the country at 6’4 and uses his mix of strength and high motor to fight for rebounds on both ends and finish through contact on a drive, a cut, or in the post. Brown is shooting an impressive 78% at the rim which is 7% higher than the next 6’6 or smaller player with 50 attempts at the rim. Brown is also a very skilled passer, and uses his ability to play anywhere on the court to find his teammates as a ball handler or as an off ball player. On the defensive end Brown has been one of the most versatile and effective defenders in the A10 as well. Brown and Arrinten Page have been the only players in the country this season to shoot 75% at the rim on at least 50 attempts, have an AST% of 15 and make 5 threes or more. Brown’s mix of finishing, rebounding, versatility, motor, defense, and passing at 6’4 make him an extremely unique and valuable player and he’s been one of the most underrated players in the country.

KJ

27,886 次观看 • 7 个月前

This High School baseball coach sounds like has his hands full. I feel for him. He kicked this senior off the baseball team. Listen to the senior laugh and then try to degrade the coach. When asked why he was kicked off he said the reason was they took him out of the game (for who knows what) and they didn’t speak to him about it. So, he got on his phone in the dugout and was texting with his mom telling her to not bother to come to the game. Everyone knows you aren’t to be on your phone in high school during a game. Just by listening to the student and also the fact the coach had an officer present, I can tell what I already need to know. Sounds like the coach is trying to turn a program around. Do you think the coach made the right decision? Context is everything I know, but listening to him, can’t you kind of gather what the issue is? Who thinks this is exactly what is wrong with our younger generation?

This High School baseball coach sounds like has his hands full. I feel for him. He kicked this senior off the baseball team. Listen to the senior laugh and then try to degrade the coach. When asked why he was kicked off he said the reason was they took him out of the game (for who knows what) and they didn’t speak to him about it. So, he got on his phone in the dugout and was texting with his mom telling her to not bother to come to the game. Everyone knows you aren’t to be on your phone in high school during a game. Just by listening to the student and also the fact the coach had an officer present, I can tell what I already need to know. Sounds like the coach is trying to turn a program around. Do you think the coach made the right decision? Context is everything I know, but listening to him, can’t you kind of gather what the issue is? Who thinks this is exactly what is wrong with our younger generation?

👉M-Û-R-Č-H👈

1,331,703 次观看 • 3 个月前

My dear people. I really don’t know what to make of it but this is really heavy stuff. I guess this is why Tom DeLonge said he couldn’t sleep for many days, I think this could be also the case for Lue Elizondo why he made the "somber" statement. It would fit the idea why former President Jimmy Carter broke down in tears after a meeting and it would match the idea of James Fox and the message of the Varginha entity: "I‘m sorry for you humans, you don’t know your potential, who you really are." I‘m connecting here many dots. Can I be wrong? Of course but this is resonating in so many ways…. And there is something more to this. I didn’t know Dr. Courtney Brown before. But it made *click* as he mentioned Remote Viewing and the Monroe institute. You will find these little details on many places in this interview. And maybe Joe Murgia is also interested in this because it’s covering the gnostic idea that the light after our death is a trap to capture the soul and recycle it to Earth as reincarnation again. So in the end Earth is a prison. This is interesting on so many levels. Here the little clip why we are here on Earth. I will post the whole interview in another comment of this tweet. Wild times!!!!!!

My dear people. I really don’t know what to make of it but this is really heavy stuff. I guess this is why Tom DeLonge said he couldn’t sleep for many days, I think this could be also the case for Lue Elizondo why he made the "somber" statement. It would fit the idea why former President Jimmy Carter broke down in tears after a meeting and it would match the idea of James Fox and the message of the Varginha entity: "I‘m sorry for you humans, you don’t know your potential, who you really are." I‘m connecting here many dots. Can I be wrong? Of course but this is resonating in so many ways…. And there is something more to this. I didn’t know Dr. Courtney Brown before. But it made click as he mentioned Remote Viewing and the Monroe institute. You will find these little details on many places in this interview. And maybe Joe Murgia is also interested in this because it’s covering the gnostic idea that the light after our death is a trap to capture the soul and recycle it to Earth as reincarnation again. So in the end Earth is a prison. This is interesting on so many levels. Here the little clip why we are here on Earth. I will post the whole interview in another comment of this tweet. Wild times!!!!!!

The Pillars Of Creation 🚫

20,669 次观看 • 1 年前

Brad Stevens on trading Jaylen Brown: "When I looked at our team and where the league was heading ... the path looked a little more challenging to me. I might be wrong - I'm not going to stand up here and be defensive about that. But the path looked a little bit more challenging with 70% of our cap and such a high percent of our usage tied into two players." The reality in this era ... you have to have the optionality to do a great job building out depth that can hopefully replace the irreplaceable individual."

Brad Stevens on trading Jaylen Brown: "When I looked at our team and where the league was heading ... the path looked a little more challenging to me. I might be wrong - I'm not going to stand up here and be defensive about that. But the path looked a little bit more challenging with 70% of our cap and such a high percent of our usage tied into two players." The reality in this era ... you have to have the optionality to do a great job building out depth that can hopefully replace the irreplaceable individual."

Erin Grugan

263,554 次观看 • 24 天前

No single day in history has impacted my life to the extent of September 11, 2001. Losing a dear friend in the tragedy sent my life into chaos and put me on a decades-long journey to uncover answers, to question narratives, and to seek clarity. Richard Gage, an architect with impeccable credentials and the founder of Architects & Engineers for 9/11 Truth, gave my search a powerful anchor. His courage to speak out, despite the cost, showed me that the truth is worth fighting for. In our heartfelt conversation, we dive deep into the events of that day, the evidence of controlled demolition, and the impact of daring to ask “why.” And, in a lively twist, towards the end of the interview, Richard offered that we share a friendly debate on the controversial “no planes” theory— a moment that sparked both passion and respect. Here is a teaser from our discussion. I hope you will join us this Thursday to watch the full interview and hear Richard's powerful answers to my questions. It was an honor of a lifetime to be able to have an interview with Richard Gage, AIA, Architect

No single day in history has impacted my life to the extent of September 11, 2001. Losing a dear friend in the tragedy sent my life into chaos and put me on a decades-long journey to uncover answers, to question narratives, and to seek clarity. Richard Gage, an architect with impeccable credentials and the founder of Architects & Engineers for 9/11 Truth, gave my search a powerful anchor. His courage to speak out, despite the cost, showed me that the truth is worth fighting for. In our heartfelt conversation, we dive deep into the events of that day, the evidence of controlled demolition, and the impact of daring to ask “why.” And, in a lively twist, towards the end of the interview, Richard offered that we share a friendly debate on the controversial “no planes” theory— a moment that sparked both passion and respect. Here is a teaser from our discussion. I hope you will join us this Thursday to watch the full interview and hear Richard's powerful answers to my questions. It was an honor of a lifetime to be able to have an interview with Richard Gage, AIA, Architect

Parallel 8 Media

25,180 次观看 • 1 年前

She was said to be below the standard of their house girl and nanny because of her comfort in her native tongue. Guess what language the accuser granted an interview in after the reunion? The same language she called her local. It turned out Mr. High Standard faked his family’s financial might 🤣🤣🤣 on the show . Over here we progress. Now look at her leveling up. This is a message of hope to everyone out there: Do not let anyone shut you down. You are an #ImisiAyanwale, if she can do it, yes you too can. Acknowledge your background and use the motivation to navigate . Good morning every where you are in the world. #BBNaija

She was said to be below the standard of their house girl and nanny because of her comfort in her native tongue. Guess what language the accuser granted an interview in after the reunion? The same language she called her local. It turned out Mr. High Standard faked his family’s financial might 🤣🤣🤣 on the show . Over here we progress. Now look at her leveling up. This is a message of hope to everyone out there: Do not let anyone shut you down. You are an #ImisiAyanwale, if she can do it, yes you too can. Acknowledge your background and use the motivation to navigate . Good morning every where you are in the world. #BBNaija

The Foxxy 🦊One

83,713 次观看 • 1 个月前

Simile CEO Joon Sung Park says their long-term goal is to simulate all 8 billion people on Earth: He says the real value isn’t just predicting what people will do - but understanding why they do it, referencing a line from the Oracle in The Matrix: ‘You’re not necessarily here to make a decision. You’ve already made the decision. You’re here to understand the decision and why you made it.’” “That captures the essence of simulation. The models we're creating aren't merely trying to predict the future - although we are good at that, and that is one of the core capabilities - but what is more important to me is understanding why we made a decision, and creating these kinds of bottom-up simulations where we can actually go back and trace through the audit logs of how society might unfold.”

Simile CEO Joon Sung Park says their long-term goal is to simulate all 8 billion people on Earth: He says the real value isn’t just predicting what people will do - but understanding why they do it, referencing a line from the Oracle in The Matrix: ‘You’re not necessarily here to make a decision. You’ve already made the decision. You’re here to understand the decision and why you made it.’” “That captures the essence of simulation. The models we're creating aren't merely trying to predict the future - although we are good at that, and that is one of the core capabilities - but what is more important to me is understanding why we made a decision, and creating these kinds of bottom-up simulations where we can actually go back and trace through the audit logs of how society might unfold.”

TBPN

113,803 次观看 • 5 个月前

Saint Louis’s Dion Brown is one of the best glue guy’s in this year’s NBA Draft. For the season Brown averaged 11/5/2 on 62/40/75 splits in only 24 MPG. While also playing a major role in Saint Louis’s 29-6 record. When it comes to role versatility and impacting the game without the ball in his hands Brown is one of the best in this year’s class. At just 6’4 Brown has the ability to play the 2-4 at a high level with his motor, strength, and instincts. Brown was one of the best finishers in the country this season where he shot 75% at the rim on 170 attempts and was the only non big to do that. Brown is an elite cutter with great instincts to get to his spots, while also being a high level slasher in the half court and he also has the ability to push in transition with and without the ball. Brown is also a strong shooter from three who shot 40% from three. Brown’s mix of shooting and finishing efficiency makes him an extremely valuable player. Brown is also a skilled passer as a connector and creator who uses his ability to get to the rim to find cutting teammates, or uses his passing vision. On the defensive end Brown was one of the best defenders in the A10 with his motor and instincts. Brown is also an elite rebounder for his height who is always attacking the glass. Browns mix of finishing, shooting, versatility, passing, rebounding, off ball scoring and defensive impact makes him one of the most valuable glue guys on any team he plays for.

Saint Louis’s Dion Brown is one of the best glue guy’s in this year’s NBA Draft. For the season Brown averaged 11/5/2 on 62/40/75 splits in only 24 MPG. While also playing a major role in Saint Louis’s 29-6 record. When it comes to role versatility and impacting the game without the ball in his hands Brown is one of the best in this year’s class. At just 6’4 Brown has the ability to play the 2-4 at a high level with his motor, strength, and instincts. Brown was one of the best finishers in the country this season where he shot 75% at the rim on 170 attempts and was the only non big to do that. Brown is an elite cutter with great instincts to get to his spots, while also being a high level slasher in the half court and he also has the ability to push in transition with and without the ball. Brown is also a strong shooter from three who shot 40% from three. Brown’s mix of shooting and finishing efficiency makes him an extremely valuable player. Brown is also a skilled passer as a connector and creator who uses his ability to get to the rim to find cutting teammates, or uses his passing vision. On the defensive end Brown was one of the best defenders in the A10 with his motor and instincts. Brown is also an elite rebounder for his height who is always attacking the glass. Browns mix of finishing, shooting, versatility, passing, rebounding, off ball scoring and defensive impact makes him one of the most valuable glue guys on any team he plays for.

KJ

51,325 次观看 • 4 个月前

"Here in sector 3, turn 12, looked good, maybe a little bit steady on picking up throttle, but watch this in turn 13, a snap of oversteer comes mid-corner just towards the exit, he has to breeze off the throttle momentarily and again in the final corner, watch the hands, he's unsure of what the rear is doing in that Ferrari and he says, you know, yet again we're going out in a session where I felt like I had the speed to go through, looked like to me just it was a tyre issue." - Anthony Davidson [video via soph]

"Here in sector 3, turn 12, looked good, maybe a little bit steady on picking up throttle, but watch this in turn 13, a snap of oversteer comes mid-corner just towards the exit, he has to breeze off the throttle momentarily and again in the final corner, watch the hands, he's unsure of what the rear is doing in that Ferrari and he says, you know, yet again we're going out in a session where I felt like I had the speed to go through, looked like to me just it was a tyre issue." - Anthony Davidson [video via soph]

sim

74,339 次观看 • 1 年前

Terrence McKenna in an interview in 1998: "I think it's just going to get weirder and weirder and weirder, and finally, it's going to be so weird that people will have to talk about how weird it is. [...] This is what it's like when a species prepares to depart for the stars. You don't depart for the stars under calm and orderly conditions. It's a fire in a madhouse, and that's what we have - the fire in the madhouse at the end of time. This is what it's like when a species prepares to move on to the next dimension."

Terrence McKenna in an interview in 1998: "I think it's just going to get weirder and weirder and weirder, and finally, it's going to be so weird that people will have to talk about how weird it is. [...] This is what it's like when a species prepares to depart for the stars. You don't depart for the stars under calm and orderly conditions. It's a fire in a madhouse, and that's what we have - the fire in the madhouse at the end of time. This is what it's like when a species prepares to move on to the next dimension."

𓆝𓆜𓆞𓆢

26,389 次观看 • 1 年前

Richard Heart Has What Elon Musk Wants Elon wants high throughput low fees and no electricity waste? Richard has it! Richard built Pulsechain to make this world better. How so? Ethereum was great once, but is not so anymore. It suffers from extremely high gas fees. The network is totally overloaded and no longer an option for the little man. Richard has forked Ethereum, which means he has taken everything that is good about ETH and turned it into something better. Pulsechain is FASTER, greener, better for the environment, more decentralized and cheaper! Do you care about Freedom? -> Pulsechain. Do you care about Freedom of Speech? -> Pulsechain Do you care about the environment? -> Pulsechain Do you care about saving money? -> Pulsechain Do you care about price performance? -> Pulsechain Do you care about decentralization? -> Pulsechain Bitcoin destroys the environment, because it's trying to maintain a secure network! This shit is dinosaur tech, it's old as the dawn of time and you are NOT an early adopter anymore. PulseChain is only a year old and it will change everyone's life in this coming bull run. Check your wallets, you have literally sitting free coins there. The biggest airdrop in history. Elon Musk and Richard Heart would make a great team! You want to be an early adopter? This one here is your chance. Perhaps a once-in-a-lifetime opportunity.

Richard Heart Has What Elon Musk Wants Elon wants high throughput low fees and no electricity waste? Richard has it! Richard built Pulsechain to make this world better. How so? Ethereum was great once, but is not so anymore. It suffers from extremely high gas fees. The network is totally overloaded and no longer an option for the little man. Richard has forked Ethereum, which means he has taken everything that is good about ETH and turned it into something better. Pulsechain is FASTER, greener, better for the environment, more decentralized and cheaper! Do you care about Freedom? -> Pulsechain. Do you care about Freedom of Speech? -> Pulsechain Do you care about the environment? -> Pulsechain Do you care about saving money? -> Pulsechain Do you care about price performance? -> Pulsechain Do you care about decentralization? -> Pulsechain Bitcoin destroys the environment, because it's trying to maintain a secure network! This shit is dinosaur tech, it's old as the dawn of time and you are NOT an early adopter anymore. PulseChain is only a year old and it will change everyone's life in this coming bull run. Check your wallets, you have literally sitting free coins there. The biggest airdrop in history. Elon Musk and Richard Heart would make a great team! You want to be an early adopter? This one here is your chance. Perhaps a once-in-a-lifetime opportunity.

Grand Inquisitor Cicero

60,464 次观看 • 2 年前

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 次观看 • 3 年前

A performer reactor once said that what makes Heeseung stand out is how his stage presence shines, even when he’s not in the spotlight. His energy and performance radiate from every corner of the stage. If he can command attention like that from the sides, imagine the impact when he’s at the center. That’s true stage power. *** DANCER REACTION: "What I like about this is that he is feeling the choreo. He is the embodiment of it. He sticks out to me in this dance practice, specifically, maybe because of his facial expressions. What I feel is an aggressive energy in the movement, but it’s not necessarily the movements themselves that are aggressive—it’s actually in his facial expressions. That’s what I really love about the balance in this section: we get that aggressive feeling not from the movement itself but from his facial expressions and the overall performance, especially in how he uses his face. I love that!" ***

A performer reactor once said that what makes Heeseung stand out is how his stage presence shines, even when he’s not in the spotlight. His energy and performance radiate from every corner of the stage. If he can command attention like that from the sides, imagine the impact when he’s at the center. That’s true stage power. * DANCER REACTION: "What I like about this is that he is feeling the choreo. He is the embodiment of it. He sticks out to me in this dance practice, specifically, maybe because of his facial expressions. What I feel is an aggressive energy in the movement, but it’s not necessarily the movements themselves that are aggressive—it’s actually in his facial expressions. That’s what I really love about the balance in this section: we get that aggressive feeling not from the movement itself but from his facial expressions and the overall performance, especially in how he uses his face. I love that!" *

• SHANTI • 🎧

35,327 次观看 • 1 年前