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。

Bird SQL is an impressive new tool, based on language models, for searching Twitter. Tools like this are changing the way we interact with information. If used in the right way, signals are becoming easier to find through the use of LLMs. Try it here:

elvis

305,232 subscribers

95,849 次观看 • 3 年前 •via X (Twitter)

教育新闻政治科学技术

Anya Rossi• Live Now

Private livecam show

10 条评论

Mike Ma (AI x Finance) 的头像

Mike Ma (AI x Finance)3 年前

@perplexity_ai cc @pinchedio

Heewon Jeon 的头像

Heewon Jeon3 年前

@memdotai mem it!

Mem 的头像

Mem3 年前

@omarsar0 Saved! Here's the compiled thread: 🪄 AI-generated summary: "Bird SQL is a new tool that allows users to search Twitter using language models. This tool can be used to find signals more easily through the use of LLMs."

Phuc Nguyen 的头像

Phuc Nguyen3 年前

@SaveToNotion

john klacynski 的头像

john klacynski3 年前

@AravSrinivas Interesting . I don’t get great results , unless I’m using a bad prompt

Farhan Ahmad 的头像

Farhan Ahmad3 年前

Doesn't show tweets any more. It shows me a paragraph on language models along with citations.

Bhavithiran 的头像

Bhavithiran3 年前

@SaveToNotion

Kishan.B 的头像

Kishan.B3 年前

@elonmusk Check this out

Exa Lovel 的头像

Exa Lovel3 年前

dude, this is impressive

Greenapps&web 的头像

Greenapps&web3 年前

@SaveToNotion #tweet #twitter

相关视频

The hard truth is that most of us know exactly what we have to do, we are just searching for an easier way to do it! Stay hard!

The hard truth is that most of us know exactly what we have to do, we are just searching for an easier way to do it! Stay hard!

David Goggins

782,511 次观看 • 2 年前

A 4-year-old child has seen 50x more information than the biggest LLMs. Yann LeCun is the Chief AI Scientist at Meta. He recently spoke on “The Expanding Universe of Generative Models” panel at the World Economic Forum in Davos. Yann highlighted the idea that a 4-year-old child is way smarter than current cutting-edge large language models (LLMs). “Think about what a child sees through vision. Put a number on how much information a 4-year-old child has seen during their life. It’s 20 Mbps going through the optical nerve for 16,000 wake hours in the first 4 years of life. 3,600 seconds per hour is 10^15 bytes. This is 50x more information than the biggest LLMs we have. A 4-year-old child is way smarter than these models having acquired an enormous amount of knowledge about how the world works.” The real constraint right now is the ability of LLMs to think. Today, LLMs are only capable of System 1 thinking. System 1 vs System 2 thinking was popularised in the book 'Thinking, Fast and Slow' by Daniel Kahneman. System 1 tasks involve quick, instinctive, automatic responses. LLMs struggle with discontinuous tasks that require a creative leap in progress as they imitate human responses. It's hard to go above human response accuracy if LLMs are only trained on humans. Models are building the track in front of them with each word being generated. What could it mean to give language models System 2 thinking? This remains a future development I'm excited about.

A 4-year-old child has seen 50x more information than the biggest LLMs. Yann LeCun is the Chief AI Scientist at Meta. He recently spoke on “The Expanding Universe of Generative Models” panel at the World Economic Forum in Davos. Yann highlighted the idea that a 4-year-old child is way smarter than current cutting-edge large language models (LLMs). “Think about what a child sees through vision. Put a number on how much information a 4-year-old child has seen during their life. It’s 20 Mbps going through the optical nerve for 16,000 wake hours in the first 4 years of life. 3,600 seconds per hour is 10^15 bytes. This is 50x more information than the biggest LLMs we have. A 4-year-old child is way smarter than these models having acquired an enormous amount of knowledge about how the world works.” The real constraint right now is the ability of LLMs to think. Today, LLMs are only capable of System 1 thinking. System 1 vs System 2 thinking was popularised in the book 'Thinking, Fast and Slow' by Daniel Kahneman. System 1 tasks involve quick, instinctive, automatic responses. LLMs struggle with discontinuous tasks that require a creative leap in progress as they imitate human responses. It's hard to go above human response accuracy if LLMs are only trained on humans. Models are building the track in front of them with each word being generated. What could it mean to give language models System 2 thinking? This remains a future development I'm excited about.

Alex Banks

22,958 次观看 • 2 年前

🚀We are excited to introduce the Tool Decathlon (Toolathlon), a benchmark for language agents on diverse, complex, and realistic tool use. ⭐️32 applications and 600+ tools based on real-world software environments ⭐️Execution-based, reliable evaluation ⭐️Realistic, covering daily and professional scenarios Toolathlon reveals significant shortcomings of SOTA LLMs in realistic tool-use tasks, where Claude Sonnet 4.5 achieves 38.6% success rate. It also indicates a clear gap between open-source and leading proprietary models. Check our blog: Github: Paper: 🧵⬇️

🚀We are excited to introduce the Tool Decathlon (Toolathlon), a benchmark for language agents on diverse, complex, and realistic tool use. ⭐️32 applications and 600+ tools based on real-world software environments ⭐️Execution-based, reliable evaluation ⭐️Realistic, covering daily and professional scenarios Toolathlon reveals significant shortcomings of SOTA LLMs in realistic tool-use tasks, where Claude Sonnet 4.5 achieves 38.6% success rate. It also indicates a clear gap between open-source and leading proprietary models. Check our blog: Github: Paper: 🧵⬇️

Junxian He

43,638 次观看 • 7 个月前

The way we look for information online is changing, and Perplexity's new web browser is just the latest way it's trying to topple Google. But can it succeed?

The way we look for information online is changing, and Perplexity's new web browser is just the latest way it's trying to topple Google. But can it succeed?

TechCrunch

22,445 次观看 • 10 个月前

Mark Zuckerberg says progress comes from inventing tools that let us observe the world in a new way, from the microscope to AI models that simulate life itself. "Most major breakthroughs are basically preceded by the invention of a new tool to observe phenomena in a new way." “And then you try to unlock those tools and give them to the scientific community to accelerate the pace.”

Mark Zuckerberg says progress comes from inventing tools that let us observe the world in a new way, from the microscope to AI models that simulate life itself. "Most major breakthroughs are basically preceded by the invention of a new tool to observe phenomena in a new way." “And then you try to unlock those tools and give them to the scientific community to accelerate the pace.”

a16z

58,755 次观看 • 7 个月前

The future of advertising is already here. Alain Afflelou’s new TV commercial is the first in Spain produced entirely with AI on Freepik (now Magnific). Last wave of tech changed the way we distribute ads, we're changing the way they are created. Congratulations to Xiaolongbao Studios, IAMbit, @Delachica_, and Valentina Roteda for leading the way, and kudos on the great result!

The future of advertising is already here. Alain Afflelou’s new TV commercial is the first in Spain produced entirely with AI on Freepik (now Magnific). Last wave of tech changed the way we distribute ads, we're changing the way they are created. Congratulations to Xiaolongbao Studios, IAMbit, @Delachica_, and Valentina Roteda for leading the way, and kudos on the great result!

Joaquín Cuenca Abela

61,385 次观看 • 9 个月前

Large Language Models (LLMs), the engines behind the likes of Chat GPT, are capable (and incapable) of many things. But are they useful for mathematicians? Jordan Ellenberg has been working on LLMs with Google DeepMind. Here are his thoughts. Full lecture:

Large Language Models (LLMs), the engines behind the likes of Chat GPT, are capable (and incapable) of many things. But are they useful for mathematicians? Jordan Ellenberg has been working on LLMs with Google DeepMind. Here are his thoughts. Full lecture:

Oxford Mathematics

31,589 次观看 • 1 年前

Introducing Bird SQL, a Twitter search interface that is powered by Perplexity’s structured search engine. It uses OpenAI Codex to translate natural language into SQL, giving everyone the ability to navigate large datasets like Twitter.

Introducing Bird SQL, a Twitter search interface that is powered by Perplexity’s structured search engine. It uses OpenAI Codex to translate natural language into SQL, giving everyone the ability to navigate large datasets like Twitter.

Perplexity

3,588,934 次观看 • 3 年前

English Is The New SQL LLMs have made it easy for everyone to create on-the-fly dashboards and plots. You can connect to your database and then use a SOTA LLM like 4o, Opus, or Gemini to generate SQL and Python code to create on-the-fly dashboards and plots. ChatLLM makes it possible across all state-of-the-art LLMs -

English Is The New SQL LLMs have made it easy for everyone to create on-the-fly dashboards and plots. You can connect to your database and then use a SOTA LLM like 4o, Opus, or Gemini to generate SQL and Python code to create on-the-fly dashboards and plots. ChatLLM makes it possible across all state-of-the-art LLMs -

Bindu Reddy

50,564 次观看 • 2 年前

The CLI is clearly becoming a dominant surface area for developer productivity. It offers an ergonomic feel that makes it easier to switch between tools. So to make our signals-based observability for agents even easier to consume, we've completely revamped plano cli to be an agent+developer friendly experience No UI installs, no additional dependencies needed - just high-fidelity agentic signals and tracing right from the cli! 🚀

The CLI is clearly becoming a dominant surface area for developer productivity. It offers an ergonomic feel that makes it easier to switch between tools. So to make our signals-based observability for agents even easier to consume, we've completely revamped plano cli to be an agent+developer friendly experience No UI installs, no additional dependencies needed - just high-fidelity agentic signals and tracing right from the cli! 🚀

Salman Paracha

11,519 次观看 • 4 个月前

KOSA will end all free speech on the internet as we know it. Elites are forcing this law through Congress. The only way to stop it is if YOU act. Here:

KOSA will end all free speech on the internet as we know it. Elites are forcing this law through Congress. The only way to stop it is if YOU act. Here:

YourFavoriteGuy

50,058 次观看 • 3 个月前

Kevin O'Connell on why excuses are easy to find when you're looking for them. "Any excuse you can find they're out there. There are excuses falling out of the rafters...Are you looking for it? Or are you immune to it?" If you’re searching for reasons, you’ll always find them. If you’re searching for solutions, you’ll find those too. One of the most reliable separators in high performance is taking ownership when it would be easier to explain yourself with excuses or reasons. 📹: Vikings

Kevin O'Connell on why excuses are easy to find when you're looking for them. "Any excuse you can find they're out there. There are excuses falling out of the rafters...Are you looking for it? Or are you immune to it?" If you’re searching for reasons, you’ll always find them. If you’re searching for solutions, you’ll find those too. One of the most reliable separators in high performance is taking ownership when it would be easier to explain yourself with excuses or reasons. 📹: Vikings

Zach Brandon

96,696 次观看 • 6 个月前

John Allan Namu: AI is a powerful tool but if you use it badly then you will get a bad outcome despite the power of the tool. Now that we are deploying this model across the most critical sectors in our economy, if we fail to get a richer understanding of the tool and fail to interrogate the intent with which we are using this tool, then we are going to end up in the situation that are in now #citizenexplainer

John Allan Namu: AI is a powerful tool but if you use it badly then you will get a bad outcome despite the power of the tool. Now that we are deploying this model across the most critical sectors in our economy, if we fail to get a richer understanding of the tool and fail to interrogate the intent with which we are using this tool, then we are going to end up in the situation that are in now #citizenexplainer

Citizen TV Kenya

11,775 次观看 • 1 个月前

used the audio in the best way possible like this is excellent use of free will atinys are so fckn funny 😭

used the audio in the best way possible like this is excellent use of free will atinys are so fckn funny 😭

mel ☾ ⋆.˚

22,079 次观看 • 1 个月前

Are you wondering how smaller accounts are getting more engagement with the new algo changes? Find out in this video below (if you don’t watch it all the way through then it’s pointless):

Are you wondering how smaller accounts are getting more engagement with the new algo changes? Find out in this video below (if you don’t watch it all the way through then it’s pointless):

Tanz Cho 💹🧲

15,067 次观看 • 1 个月前

Joy Kirigia, Investigative Journalist: We were able to get into the SHA system based on the information that we got in order to find out how it works. What we managed to do is try to understand how this system calculates the premiums for Kenyans. What we managed to find out is that it overcharges the poorest of this group of people who are in the informal sector and undercharges the richest group of people in this same informal sector #CitizenExplainer

Joy Kirigia, Investigative Journalist: We were able to get into the SHA system based on the information that we got in order to find out how it works. What we managed to do is try to understand how this system calculates the premiums for Kenyans. What we managed to find out is that it overcharges the poorest of this group of people who are in the informal sector and undercharges the richest group of people in this same informal sector #CitizenExplainer

Citizen TV Kenya

24,729 次观看 • 1 个月前

I'm exploring running LLMs locally on iPhones and Macs. I’ve got Llama 3.2 running locally using Apple’s MLX and with support for tool calling. This example runs two LLMs: one to identify tools to call based on the query and one to generate responses based on the tools’ outputs.

I'm exploring running LLMs locally on iPhones and Macs. I’ve got Llama 3.2 running locally using Apple’s MLX and with support for tool calling. This example runs two LLMs: one to identify tools to call based on the query and one to generate responses based on the tools’ outputs.

Simon B. Støvring

47,972 次观看 • 1 年前

"If an independent redistricting commission is standing in your way, roll it the fuck over it. If the filibuster is standing in your way, if the parliamentarian is standing in your way, if any good government reforms are standing in your way, barrel through those things."

"If an independent redistricting commission is standing in your way, roll it the fuck over it. If the filibuster is standing in your way, if the parliamentarian is standing in your way, if any good government reforms are standing in your way, barrel through those things."

Brian Tyler Cohen

25,727 次观看 • 9 个月前

DeepMind just dropped Lyria, a state-of-the-art music generative model. Last year, I said 2022 was the year of pixels and 2023 would be the year of soundwaves. We are making great progress here! The most impressive demo is converting humming to a full instrument suite. I think Lyria will unlock all the operators we are used to in image models: text-based editing, style transfer, in-painting (fill out tracks), out-painting (continue a track), super-resolution, etc. Lyria is deployed as an intuitive software tool to musicians, in partnership with YouTube. This is the right move: ship the model! With enough artists on board, Lyria could spin a data flywheel that learns from the artists' feedback and editing signals. Congrats to DeepMind for shipping! Launch blog:

DeepMind just dropped Lyria, a state-of-the-art music generative model. Last year, I said 2022 was the year of pixels and 2023 would be the year of soundwaves. We are making great progress here! The most impressive demo is converting humming to a full instrument suite. I think Lyria will unlock all the operators we are used to in image models: text-based editing, style transfer, in-painting (fill out tracks), out-painting (continue a track), super-resolution, etc. Lyria is deployed as an intuitive software tool to musicians, in partnership with YouTube. This is the right move: ship the model! With enough artists on board, Lyria could spin a data flywheel that learns from the artists' feedback and editing signals. Congrats to DeepMind for shipping! Launch blog:

Jim Fan

384,184 次观看 • 2 年前