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。

MIT Researchers destroyed context window limits. 10m+ token prompts are now possible by moving context out of the model and into code environments. Full breakdown below.

Matthew Berman

126,992 subscribers

287,551 次观看 • 5 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

Google announces Gemini 1.5 blog: Gemini 1.5 Pro, mid-sized model, will soon come standard with a 128K-token context window, but starting today, developers + customers can sign up for the limited Private Preview to try out 1.5 Pro with a groundbreaking and experimental 1 million token context window

Google announces Gemini 1.5 blog: Gemini 1.5 Pro, mid-sized model, will soon come standard with a 128K-token context window, but starting today, developers + customers can sign up for the limited Private Preview to try out 1.5 Pro with a groundbreaking and experimental 1 million token context window

AK

13,850 次观看 • 2 年前

This is Claude Sonnet 4.6: our most capable Sonnet model yet. It’s a full upgrade across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. It also features a 1M token context window in beta.

This is Claude Sonnet 4.6: our most capable Sonnet model yet. It’s a full upgrade across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. It also features a 1M token context window in beta.

Claude

7,594,755 次观看 • 4 个月前

From no dev experience to a fully built out RPG game in a week and a half for @levelsio #vibejam (and also the Solana Developers side jam). Coming in at over 14,000 lines of code (I wrote none of them) 🤯 Massive learning experience writing hundreds of prompts, overcoming rate limits, context window limitations, and major refactoring and debugging challenges. Feeling inspired by what's possible with the latest AI tools and already itching to build more.

From no dev experience to a fully built out RPG game in a week and a half for @levelsio #vibejam (and also the Solana Developers side jam). Coming in at over 14,000 lines of code (I wrote none of them) 🤯 Massive learning experience writing hundreds of prompts, overcoming rate limits, context window limitations, and major refactoring and debugging challenges. Feeling inspired by what's possible with the latest AI tools and already itching to build more.

Lewis

58,253 次观看 • 1 年前

CONTEXT ENGINEERING > PROMPT ENGINEERING Everyone is obsessed with writing better prompts. The next generation of AI builders is focused on context engineering instead. • Prompt engineering shapes the question. Context engineering shapes everything the AI sees. • Great prompts can't save an agent missing critical context, memory, or tools. • AI failures often come from missing information, not weak models. • Context engineering combines prompts, memory, RAG, state management, and tool access into one system. What powers effective AI agents? → Memory: Remembers preferences, past interactions, and ongoing tasks. → State Management: Tracks progress across multi-step workflows. → RAG: Retrieves only the most relevant information when needed. → Tools: Connects AI to APIs, databases, code execution, and real-world actions. → Dynamic Prompts: Enriches instructions with live context at runtime. The key insight: Prompt Engineering = Better Questions Context Engineering = Better Systems The future of AI isn't building smarter prompts. It's building smarter environments for AI to think, remember, retrieve, and act.

CONTEXT ENGINEERING > PROMPT ENGINEERING Everyone is obsessed with writing better prompts. The next generation of AI builders is focused on context engineering instead. • Prompt engineering shapes the question. Context engineering shapes everything the AI sees. • Great prompts can't save an agent missing critical context, memory, or tools. • AI failures often come from missing information, not weak models. • Context engineering combines prompts, memory, RAG, state management, and tool access into one system. What powers effective AI agents? → Memory: Remembers preferences, past interactions, and ongoing tasks. → State Management: Tracks progress across multi-step workflows. → RAG: Retrieves only the most relevant information when needed. → Tools: Connects AI to APIs, databases, code execution, and real-world actions. → Dynamic Prompts: Enriches instructions with live context at runtime. The key insight: Prompt Engineering = Better Questions Context Engineering = Better Systems The future of AI isn't building smarter prompts. It's building smarter environments for AI to think, remember, retrieve, and act.

Dami-Defi

10,120 次观看 • 28 天前

Mike Johnson now claims he didn't say what he said: "They took a clip out of context." (The clip is not out of context. Watch it below.)

Mike Johnson now claims he didn't say what he said: "They took a clip out of context." (The clip is not out of context. Watch it below.)

Aaron Rupar

1,714,772 次观看 • 1 年前

Our new model Claude 2.1 offers an industry-leading 200K token context window, a 2x decrease in hallucination rates, system prompts, tool use, and updated pricing. Claude 2.1 is available over API in our Console, and is powering our chat experience.

Our new model Claude 2.1 offers an industry-leading 200K token context window, a 2x decrease in hallucination rates, system prompts, tool use, and updated pricing. Claude 2.1 is available over API in our Console, and is powering our chat experience.

Anthropic

1,872,198 次观看 • 2 年前

You can now organize chats with Claude into shareable Projects. Each project includes a 200K context window, so you can include relevant documents, code, and files.

You can now organize chats with Claude into shareable Projects. Each project includes a 200K context window, so you can include relevant documents, code, and files.

Anthropic

501,497 次观看 • 2 年前

Introducing Claude Code Hook - Context Timeline (Saving this to try later) Install with: npx claude-code-templates@latest --hook monitoring/context-timeline Managing the context window and the subagents running in Claude Code is hard to keep track of That's why I built this hook... It starts the moment you open a session and shows a timeline with the main agent's context window and how subagents start working in their own separate context Every subagent you have running will show up in real time This way you can manage the context and the subagents you run, and see everything in a much simpler way than in the console

Introducing Claude Code Hook - Context Timeline (Saving this to try later) Install with: npx claude-code-templates@latest --hook monitoring/context-timeline Managing the context window and the subagents running in Claude Code is hard to keep track of That's why I built this hook... It starts the moment you open a session and shows a timeline with the main agent's context window and how subagents start working in their own separate context Every subagent you have running will show up in real time This way you can manage the context and the subagents you run, and see everything in a much simpler way than in the console

Daniel San

51,642 次观看 • 2 个月前

Woot! The multimodal party is really getting started now. Check out Gemini 1.5 pro in action below ⤵️ With a mind boggling 1M token context window you can talk to full length movies, podcasts, and a boat load of docs. Also props to Google for being ultra transparent about the demos this time.

Woot! The multimodal party is really getting started now. Check out Gemini 1.5 pro in action below ⤵️ With a mind boggling 1M token context window you can talk to full length movies, podcasts, and a boat load of docs. Also props to Google for being ultra transparent about the demos this time.

Bilawal Sidhu

20,910 次观看 • 2 年前

🚨 Breaking: Google will soon launch Gemini CLI, a powerful open-source AI agent built for the terminal. - Built on Gemini 2.5 Pro - 1 million token context window - Free tier with 60 requests per minute and 1,000 per day - Google Search grounding for real-time context - Script and plugin support - Non-interactive mode for automation - Support for Model Context Protocol (MCP) - Integrated with Gemini Code Assist in VS Code - Fully open-source under Apache 2.0

🚨 Breaking: Google will soon launch Gemini CLI, a powerful open-source AI agent built for the terminal. - Built on Gemini 2.5 Pro - 1 million token context window - Free tier with 60 requests per minute and 1,000 per day - Google Search grounding for real-time context - Script and plugin support - Non-interactive mode for automation - Support for Model Context Protocol (MCP) - Integrated with Gemini Code Assist in VS Code - Fully open-source under Apache 2.0

AshutoshShrivastava

217,397 次观看 • 1 年前

The reality in enterprise AI = context > models Jaya Gupta & Arvind Jain dig into this topic and where AI breaks down in practice, who should own the context graph, and whether context graphs are really a trillion-dollar opportunity. Watch the full conversation linked below 👇

The reality in enterprise AI = context > models Jaya Gupta & Arvind Jain dig into this topic and where AI breaks down in practice, who should own the context graph, and whether context graphs are really a trillion-dollar opportunity. Watch the full conversation linked below 👇

Glean

42,269 次观看 • 2 个月前

Design → code → canvas → feedback → repeat. The Figma MCP server is now bidirectional. GitHub Copilot users can pull design context into code and push working UI back to the Figma canvas, all from Visual Studio Code . No handoffs or context switching. Just flow.

Design → code → canvas → feedback → repeat. The Figma MCP server is now bidirectional. GitHub Copilot users can pull design context into code and push working UI back to the Figma canvas, all from Visual Studio Code . No handoffs or context switching. Just flow.

Mario Rodriguez

105,792 次观看 • 4 个月前

In December, we launched Gemini 1.0 Pro. Today, we're introducing Gemini 1.5 Pro! 🚀 This next-gen model uses a Mixture-of-Experts (MoE) approach for more efficient training & higher-quality responses. Gemini 1.5 Pro, our mid-sized model, will soon come standard with a 128K-token context window, but starting today, developers + customers can sign up for the limited Private Preview to try out 1.5 Pro with a groundbreaking and experimental 1 million token context window! The 1M tokens feature unlocks huge possibilities for devs - upload hundreds of pages of text, entire code repos, and long videos and let Gemini reason across them. It's still experimental and early and we’d love your feedback - learn more here.

In December, we launched Gemini 1.0 Pro. Today, we're introducing Gemini 1.5 Pro! 🚀 This next-gen model uses a Mixture-of-Experts (MoE) approach for more efficient training & higher-quality responses. Gemini 1.5 Pro, our mid-sized model, will soon come standard with a 128K-token context window, but starting today, developers + customers can sign up for the limited Private Preview to try out 1.5 Pro with a groundbreaking and experimental 1 million token context window! The 1M tokens feature unlocks huge possibilities for devs - upload hundreds of pages of text, entire code repos, and long videos and let Gemini reason across them. It's still experimental and early and we’d love your feedback - learn more here.

Sundar Pichai

852,598 次观看 • 2 年前

We just added Prompt Completions to Augment for VS Code. You’ll now get context-aware suggestions as you type prompts for your agent — including natural-language completions, variable names, file references, and more. It makes writing great prompts faster, especially for users who craft long specs or detailed instructions. Powered by full codebase context and agent history, so agent prompt completions feel in sync with what users are trying to write.

We just added Prompt Completions to Augment for VS Code. You’ll now get context-aware suggestions as you type prompts for your agent — including natural-language completions, variable names, file references, and more. It makes writing great prompts faster, especially for users who craft long specs or detailed instructions. Powered by full codebase context and agent history, so agent prompt completions feel in sync with what users are trying to write.

Augment Code

593,917 次观看 • 7 个月前

🚨 2 NEW Claude Code features are rolling out! - BRAND NEW /context command - 1 MILLION context windows (!!) Thankful to be a part of the v1.0.88 beta cohort! 👇 FAQ in comments:

Adam

62,809 次观看 • 10 个月前

I'm excited that Visual Studio Code (Insiders) now supports the full Model Context Protocol (MCP) spec, including sampling! ⚡ I just published a new blog post and video showing how you can use sampling to generate tags for journal entries in an MCP-powered app. Check out what’s possible!

I'm excited that Visual Studio Code (Insiders) now supports the full Model Context Protocol (MCP) spec, including sampling! ⚡ I just published a new blog post and video showing how you can use sampling to generate tags for journal entries in an MCP-powered app. Check out what’s possible!

Kent C. Dodds ⚡

189,564 次观看 • 1 年前

We're rolling out new features to help you create longer, more coherent tracks. First, extensions now use a context-window of up to two minutes, increased from 30 seconds. This means verse and chorus structures are more consistent. Check out the example below! (h/t user DrGoldenPants)

We're rolling out new features to help you create longer, more coherent tracks. First, extensions now use a context-window of up to two minutes, increased from 30 seconds. This means verse and chorus structures are more consistent. Check out the example below! (h/t user DrGoldenPants)

udio

137,242 次观看 • 2 年前