Загрузка видео...

Не удалось загрузить видео

На главную

Sylvian (Sylvian) creates tool use environments and gathers expert tool use data (VSCode, Excel, etc.) for LLMs. They already have 4,500+ experts, from IMO Golds to MIT/Stanford PhDs, producing data at 1B tokens/wk.

ycombinator's profile picture

Y Combinator

1,601,384 subscribers

34,674 просмотров • 8 месяцев назад •via X (Twitter)

ОбразованиеНовости и политикаНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Use this FREE tool to analyze data in 10 sec. This tool is used by more than 500,000 researchers. 1. Go to 2. Click on Data Analysis and upload your data file. 3. Write your prompt for data analysis. 4. For example, generate graphs from data. 5. AnswerThis will generate variety of graphs 6. It also generates an insightful data analysis report. You can download the graphs and the report. Try AnswerThis today. It’s FREE.
0:32

Use this FREE tool to analyze data in 10 sec. This tool is used by more than 500,000 researchers. 1. Go to 2. Click on Data Analysis and upload your data file. 3. Write your prompt for data analysis. 4. For example, generate graphs from data. 5. AnswerThis will generate variety of graphs 6. It also generates an insightful data analysis report. You can download the graphs and the report. Try AnswerThis today. It’s FREE.

Faheem Ullah

26,452 просмотров • 5 месяцев назад

Excel is finished. Imagine having a personal AI analyst for your data. This tool changes everything:
0:32

Excel is finished. Imagine having a personal AI analyst for your data. This tool changes everything:

Alex Banks

369,974 просмотров • 3 лет назад

How to use the INDEX + MATCH functions to search for data in Excel‼️ ❤️ and follow CheatSheets for daily tips‼️ #excel
0:53

How to use the INDEX + MATCH functions to search for data in Excel‼️ ❤️ and follow CheatSheets for daily tips‼️ #excel

CheatSheets

27,822 просмотров • 2 лет назад

Fixpoint (fixpoint) automates hiring vetted experts—doctors, lawyers, PhDs, coders, etc—for AI training data and evals. They handle sourcing and vetting so customers can focus on creating quality data and benchmarking AI. Congrats on the launch, Dylan Mikus and Jakub!
1:18

Fixpoint (fixpoint) automates hiring vetted experts—doctors, lawyers, PhDs, coders, etc—for AI training data and evals. They handle sourcing and vetting so customers can focus on creating quality data and benchmarking AI. Congrats on the launch, Dylan Mikus and Jakub!

Y Combinator

11,883 просмотров • 8 месяцев назад

Using tools is often regarded as the hallmark of intelligence. How can robots creatively use tools beyond standard functionalities and make impossible tasks possible? 🤖🗝️ We introduce RoboTool built on LLMs, enabling multiple creative tool-use behaviors, including tool selection, sequential tool use, and tool manufacturing!🧵👇🏼
1:48

Using tools is often regarded as the hallmark of intelligence. How can robots creatively use tools beyond standard functionalities and make impossible tasks possible? 🤖🗝️ We introduce RoboTool built on LLMs, enabling multiple creative tool-use behaviors, including tool selection, sequential tool use, and tool manufacturing!🧵👇🏼

Mengdi Xu

48,218 просмотров • 2 лет назад

PhD Students – Use this FREE tool to analyze data in 10 sec. This tool is used by more than 500,000 researchers. 1. Go to 2. Click on Data Analysis and upload your data file. 3. Write your prompt for data analysis. 4. For example, generate graphs for data analysis. 5. AnswerThis will generate variety of graphs for you. 6. It also generates an insightful data analysis report. You can download the graphs and the report. Try AnswerThis today. It’s FREE. AnswerThis link:
0:29

PhD Students – Use this FREE tool to analyze data in 10 sec. This tool is used by more than 500,000 researchers. 1. Go to 2. Click on Data Analysis and upload your data file. 3. Write your prompt for data analysis. 4. For example, generate graphs for data analysis. 5. AnswerThis will generate variety of graphs for you. 6. It also generates an insightful data analysis report. You can download the graphs and the report. Try AnswerThis today. It’s FREE. AnswerThis link:

Faheem Ullah

205,901 просмотров • 3 месяцев назад

Groq function calling is incredible Powered entirely by @GlaiveAI synthetic data! Instant tool-use is going to be massive... Utterly insane to use (watch the full video)
0:21

Groq function calling is incredible Powered entirely by @GlaiveAI synthetic data! Instant tool-use is going to be massive... Utterly insane to use (watch the full video)

Matt Shumer

43,961 просмотров • 2 лет назад

Your business does not need Excel to excel. Listen to Kumar and use Emergent to create a tool for your business with no coding! 👨‍💻 Emergent #emergent #Ad
1:00

Your business does not need Excel to excel. Listen to Kumar and use Emergent to create a tool for your business with no coding! 👨‍💻 Emergent #emergent #Ad

Danish Sait

1,704,333 просмотров • 12 дней назад

Run Python with the Gemini API. Nikita Namjoshi shares how to use the Code Execution tool in AI Studio to solve math problems, perform data analysis, and use code-based reasoning.
4:48

Run Python with the Gemini API. Nikita Namjoshi shares how to use the Code Execution tool in AI Studio to solve math problems, perform data analysis, and use code-based reasoning.

Google AI Developers

16,481 просмотров • 7 месяцев назад

Unified generation API? ✅ Structured data? ✅ Tool calling? ✅ Vector search? ✅ That’s right: Genkit for Node.js is now at version 1.0 and ready for production use. Read the blog →
0:48

Unified generation API? ✅ Structured data? ✅ Tool calling? ✅ Vector search? ✅ That’s right: Genkit for Node.js is now at version 1.0 and ready for production use. Read the blog →

Firebase

12,092 просмотров • 1 год назад

ICYMI: We launched Data Agent Kit, a unified, open-source collection of data engineering and data science skills, tools, and plugins that integrate into the environments practitioners already use—VS Code, Claude Code, Codex, Antigravity CLI, and more →
0:56

ICYMI: We launched Data Agent Kit, a unified, open-source collection of data engineering and data science skills, tools, and plugins that integrate into the environments practitioners already use—VS Code, Claude Code, Codex, Antigravity CLI, and more →

Google Cloud Tech

24,413 просмотров • 28 дней назад

With Llama 3.2 we released our first-ever lightweight Llama models: 1B & 3B. These models empower developers to build personalized, on-device agentic applications with capabilities like summarization, tool use and RAG where data never leaves the device.
0:45

With Llama 3.2 we released our first-ever lightweight Llama models: 1B & 3B. These models empower developers to build personalized, on-device agentic applications with capabilities like summarization, tool use and RAG where data never leaves the device.

AI at Meta

153,348 просмотров • 1 год назад

"We already have to use JavaScript for the front end, so instead of learning another tool, we just use it on the back end, too" "JavaScript everywhere"
0:40

"We already have to use JavaScript for the front end, so instead of learning another tool, we just use it on the back end, too" "JavaScript everywhere"

Patrick Collins

36,244 просмотров • 1 год назад

Imitation learning is great, but needs us to have (near) optimal data. We throw away most other data (failures, evaluation data, suboptimal data, undirected play data), even though this data can be really useful and way cheaper! In our new work - RISE, we show a simple way to *use all of this non-optimal data to robustify imitation learning* with minimal requirements beyond BC. Key idea: use non-expert data to learn how to *recover* back to expert data with a minimal frills offline RL that works under sparse data coverage. Allows usage of *all* available data, not just expert data - never throw your data away! Paper: Website: A 🧵(1/10)
0:57

Imitation learning is great, but needs us to have (near) optimal data. We throw away most other data (failures, evaluation data, suboptimal data, undirected play data), even though this data can be really useful and way cheaper! In our new work - RISE, we show a simple way to *use all of this non-optimal data to robustify imitation learning* with minimal requirements beyond BC. Key idea: use non-expert data to learn how to *recover* back to expert data with a minimal frills offline RL that works under sparse data coverage. Allows usage of *all* available data, not just expert data - never throw your data away! Paper: Website: A 🧵(1/10)

Abhishek Gupta

20,595 просмотров • 8 месяцев назад

Introducing Web Scraper - a tiny tool to extract data from any website. Extract data from any site Zero config Dev-friendly
0:45

Introducing Web Scraper - a tiny tool to extract data from any website. Extract data from any site Zero config Dev-friendly

Mohd Danish

140,876 просмотров • 5 месяцев назад

Today we're launching Subconscious: a new platform for building agents with long-horizon reasoning and tool use, backed by MIT research. One API call. Tool use. Context beyond existing limits. If you're building agents, let's talk.
1:44

Today we're launching Subconscious: a new platform for building agents with long-horizon reasoning and tool use, backed by MIT research. One API call. Tool use. Context beyond existing limits. If you're building agents, let's talk.

Jack O'Brien

12,077 просмотров • 11 месяцев назад

📊🤓Calling all UK data nerds. From today, there's an exciting new way to get #Census2021 data for any set of variables you like. Use the Office for National Statistics (ONS) "Create a custom dataset" tool to build your own multi-variate tables (for England & Wales). 1/3
0:52

📊🤓Calling all UK data nerds. From today, there's an exciting new way to get #Census2021 data for any set of variables you like. Use the Office for National Statistics (ONS) "Create a custom dataset" tool to build your own multi-variate tables (for England & Wales). 1/3

Ahmad Barclay

53,586 просмотров • 3 лет назад