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。

today we're releasing a new small model (0.5B) for detecting problems with tool usage in agents, trained on 50M tokens from publicly available MCP server tools it's great at picking up on tool accuracy issues and outperforms larger models

Freddie Vargus

1,413 subscribers

96,781 次观看 • 1 年前 •via X (Twitter)

健康养生科学技术教育

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

Introducing VisionPsy-Nano: state-of-the-art vision-language models at 460M parameters, small enough to run on the phone in your pocket. VisionPsy-Nano-460M leads every other ~0.5B vision-language model tested & compares favourably on 16 of 17 benchmarks, tops all four capability categories, and outperforms models up to 2.3x larger. Two variants, one tuned for maximum accuracy and one for real-time responsiveness. Open weights, Apache 2.0, and no cloud in the loop.

Introducing VisionPsy-Nano: state-of-the-art vision-language models at 460M parameters, small enough to run on the phone in your pocket. VisionPsy-Nano-460M leads every other ~0.5B vision-language model tested & compares favourably on 16 of 17 benchmarks, tops all four capability categories, and outperforms models up to 2.3x larger. Two variants, one tuned for maximum accuracy and one for real-time responsiveness. Open weights, Apache 2.0, and no cloud in the loop.

QVAC

15,325,247 次观看 • 25 天前

Aero blade removal on the new Model Y as simple as a quick pull on the small ones, and using a trim removal tool to free up the larger ones.

Aero blade removal on the new Model Y as simple as a quick pull on the small ones, and using a trim removal tool to free up the larger ones.

TESLA CARS ONLY⚡️

45,503 次观看 • 3 个月前

DigitalOcean’s model synthesis tool is now available in public preview. 🆕 A new server-side tool: run multiple models on one inference request and get a single synthesized response, no custom orchestration. Just add it to your existing inference request.

DigitalOcean’s model synthesis tool is now available in public preview. 🆕 A new server-side tool: run multiple models on one inference request and get a single synthesized response, no custom orchestration. Just add it to your existing inference request.

DigitalOcean

2,030,708 次观看 • 1 个月前

Portkey's MCP Gateway is now GA. MCP has truly exploded. Trillions of tokens flow through our infra every month. Agents can finally do things: hit databases, trigger workflows, access internal systems. But auth is fragmented. There's no access control. And once multiple agents are involved, it's impossible to know what can access what. Today we're fixing that. One line to connect any MCP server. Centralized authentication. Fine-grained access control by team, by tool, by action. Full observability on every tool call. Platform teams can finally say yes to agents without losing sleep. Already live with Fortune 50.

Portkey's MCP Gateway is now GA. MCP has truly exploded. Trillions of tokens flow through our infra every month. Agents can finally do things: hit databases, trigger workflows, access internal systems. But auth is fragmented. There's no access control. And once multiple agents are involved, it's impossible to know what can access what. Today we're fixing that. One line to connect any MCP server. Centralized authentication. Fine-grained access control by team, by tool, by action. Full observability on every tool call. Platform teams can finally say yes to agents without losing sleep. Already live with Fortune 50.

Rohit Agarwal

175,553 次观看 • 7 个月前

New in AdHoc tools: * Sweep Arc (Cross between ResizeAlign and GapFill) * Resize Each Part (behavior from F3X / SBS) Make your tool request today... In the Discord server: On the plugin page:

New in AdHoc tools: * Sweep Arc (Cross between ResizeAlign and GapFill) * Resize Each Part (behavior from F3X / SBS) Make your tool request today... In the Discord server: On the plugin page:

Stravant

66,169 次观看 • 6 个月前

LFM2.5-ColBERT-350M is a surprisingly reliable smart tool selector. We gave it 151 tools, and it consistently surfaces the 5 most relevant ones based on the user prompt. This saves tokens and improves accuracy. Ideal for hmmmm agentic edge models? 👀

LFM2.5-ColBERT-350M is a surprisingly reliable smart tool selector. We gave it 151 tools, and it consistently surfaces the 5 most relevant ones based on the user prompt. This saves tokens and improves accuracy. Ideal for hmmmm agentic edge models? 👀

Maxime Labonne

19,216 次观看 • 2 个月前

Skiff is a new, small tool for deploying static marketing sites using Kamal. Built on #NoBuild ideas, stone-age tools like Server Side Includes, and running with nginx. We use it to run and already. Enjoy!

Skiff is a new, small tool for deploying static marketing sites using Kamal. Built on #NoBuild ideas, stone-age tools like Server Side Includes, and running with nginx. We use it to run and already. Enjoy!

DHH

130,445 次观看 • 2 年前

Breaking 👀💥! Today, we're introducing the Scenario Discord Bot – a tool transforming how gaming communities create stunning art. Get ready for style-consistent image generation on every Discord server, via custom-trained AI models. LIVE on 1/9 🧵👇

Breaking 👀💥! Today, we're introducing the Scenario Discord Bot – a tool transforming how gaming communities create stunning art. Get ready for style-consistent image generation on every Discord server, via custom-trained AI models. LIVE on 1/9 🧵👇

Emm | scenario.com

207,652 次观看 • 3 年前

HERMES AGENT WITHOUT TOOLS IS A CHATBOT. WITH THEM IT BUILDS 3D TOWERS IN BLENDER, CHECKS STOCK PRICES, AND DRIVES VS CODE. tonbi JUST DROPPED THE FULL GUIDE. module 6 of his 10-part Hermes masterclass. best breakdown of the tool layer anyone has published. what you need to know: TOOLS vs SKILLS vs MCP skills = instructions (markdown, loaded into context) tools = callable functions (Python, agent emits call, Hermes executes) MCP = adapters to external systems (Blender, Stripe, Linear, Notion) every tool has three parts: → the function (does the real work) → the schema (what the model sees to decide when to call it) → the registry (makes the tool exist in the agent) the model never runs the function directly. it emits a structured request (tool name + JSON args). Hermes executes and returns the result. if the tool fails, the error goes back as JSON. the agent recovers instead of crashing. TOOL SETS CONTROL THE SURFACE hermes chat --tool-sets web # only web tools loaded. no files, no terminal. hermes chat --tool-sets safe # read-only: web search, vision, image gen. # no file writes. no terminal. no code execution. mid-session: /tools enable video /tools disable terminal or toggle in the dashboard: hermes dashboard → Skills → Tool Sets MCP SERVERS two transport types: STDIO (local subprocess) or HTTP (remote endpoint). add a server: hermes mcp # or ask: "add the MCP server for Blender" filter tools with include/exclude per server. keep only what you trust. security: → OAuth 2.1 PKCE (no long-lived tokens in config) → package scanning via api.osv. dev before launch → all MCP calls go through approval gates HERMES AS MCP SERVER hermes mcp serve exposes 10 tools via FastMCP. connect VS Code Copilot or Cursor to your running Hermes instance. BUILD YOUR OWN TOOL He built a stock price tool live: → Python function calling Finnhub API → schema with name, description, parameters → registered in tool_sets.py → agent calls it automatically when relevant any repeating API call in your workflow can become a native tool. full Hermes architecture deep-dive in the article 👇

HERMES AGENT WITHOUT TOOLS IS A CHATBOT. WITH THEM IT BUILDS 3D TOWERS IN BLENDER, CHECKS STOCK PRICES, AND DRIVES VS CODE. tonbi JUST DROPPED THE FULL GUIDE. module 6 of his 10-part Hermes masterclass. best breakdown of the tool layer anyone has published. what you need to know: TOOLS vs SKILLS vs MCP skills = instructions (markdown, loaded into context) tools = callable functions (Python, agent emits call, Hermes executes) MCP = adapters to external systems (Blender, Stripe, Linear, Notion) every tool has three parts: → the function (does the real work) → the schema (what the model sees to decide when to call it) → the registry (makes the tool exist in the agent) the model never runs the function directly. it emits a structured request (tool name + JSON args). Hermes executes and returns the result. if the tool fails, the error goes back as JSON. the agent recovers instead of crashing. TOOL SETS CONTROL THE SURFACE hermes chat --tool-sets web # only web tools loaded. no files, no terminal. hermes chat --tool-sets safe # read-only: web search, vision, image gen. # no file writes. no terminal. no code execution. mid-session: /tools enable video /tools disable terminal or toggle in the dashboard: hermes dashboard → Skills → Tool Sets MCP SERVERS two transport types: STDIO (local subprocess) or HTTP (remote endpoint). add a server: hermes mcp # or ask: "add the MCP server for Blender" filter tools with include/exclude per server. keep only what you trust. security: → OAuth 2.1 PKCE (no long-lived tokens in config) → package scanning via api.osv. dev before launch → all MCP calls go through approval gates HERMES AS MCP SERVER hermes mcp serve exposes 10 tools via FastMCP. connect VS Code Copilot or Cursor to your running Hermes instance. BUILD YOUR OWN TOOL He built a stock price tool live: → Python function calling Finnhub API → schema with name, description, parameters → registered in tool_sets.py → agent calls it automatically when relevant any repeating API call in your workflow can become a native tool. full Hermes architecture deep-dive in the article 👇

YanXbt

32,680 次观看 • 2 个月前

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

The MiniMax M2 model is mind-blowing! It's open-source. It outperforms Gemini 2.5, Claude 4.1, and Qwen3 across coding and tool-use benchmarks. Right now, it's one of the world's top 5 models in intelligence! And here is the best part: Claude is one of the best models you can use today, and MiniMax M2 costs only 8% of that! It's smaller, faster, and cheaper. Extremely efficient at using tokens. Minimax M2's biggest strength: High agentic capabilities. The model can plan and execute complex multi-tool workflows. It's reliable and very robust at executing long-horizon tool chains. In summary: • Low latency • Very cheap • Excels at agentic tasks • Open-source The model currently powers the MiniMax Agent and is available for a free global trial. You can access MiniMax M2's API here: To access the agent: And here is the MiniMax website: Thanks to the MiniMax team for showing me the ropes and partnering with me on this post.

Santiago

91,197 次观看 • 9 个月前

Today we're launching the new Activity explorer on OpenRouter. It's the best way to see how much and your team are spending on every model, along with tokens, cache hit rate, agents, & trends. All updated in real time. See how our team is using Fable and other models 👇

Today we're launching the new Activity explorer on OpenRouter. It's the best way to see how much and your team are spending on every model, along with tokens, cache hit rate, agents, & trends. All updated in real time. See how our team is using Fable and other models 👇

OpenRouter

37,372 次观看 • 2 个月前

Introducing Mintlify Index: the first publisher-direct search layer for technical knowledge, built on Mintlify’s ecosystem of more than 200,000 orgs. In our benchmark against Context7, agents using Mintlify Index finished tasks at twice the speed, and with 9% higher factual accuracy. Today, we're opening up the Index MCP server for everyone to try, fully for free:

Introducing Mintlify Index: the first publisher-direct search layer for technical knowledge, built on Mintlify’s ecosystem of more than 200,000 orgs. In our benchmark against Context7, agents using Mintlify Index finished tasks at twice the speed, and with 9% higher factual accuracy. Today, we're opening up the Index MCP server for everyone to try, fully for free:

Mintlify

149,257 次观看 • 17 天前

Kimi K3 is available for FREE on TokenRouter 50,000,000 FREE tokens 1) Sign up at 2) Create an API key in the "API keys" 3) Use these settings in any OpenAI-compatible tool: - Base URL: ' ' - API Key: ' your new key ' - Model: ' moonshotai/kimi-k3-free ' Done. Works in Cursor, Claude Code, Cline, OpenCode and similar tools

Kimi K3 is available for FREE on TokenRouter 50,000,000 FREE tokens 1) Sign up at 2) Create an API key in the "API keys" 3) Use these settings in any OpenAI-compatible tool: - Base URL: ' ' - API Key: ' your new key ' - Model: ' moonshotai/kimi-k3-free ' Done. Works in Cursor, Claude Code, Cline, OpenCode and similar tools

beamnxw ./

50,807 次观看 • 23 天前

Church Matters is now available on subscription. It's a tool to disciple your elders or read through with someone you are raising up. Subscribe today at

Church Matters is now available on subscription. It's a tool to disciple your elders or read through with someone you are raising up. Subscribe today at

9Marks

13,004 次观看 • 1 年前

Cline can now create and add tools to himself using MCP! Try asking him to “add a tool that pulls the latest npm docs” - Cline handles everything from creating the MCP server to installing it *into himself*, ready for future tasks. Servers are saved in ~/Documents/Cline/MCP so you can easily share tools with friends!

Cline can now create and add tools to himself using MCP! Try asking him to “add a tool that pulls the latest npm docs” - Cline handles everything from creating the MCP server to installing it into himself, ready for future tasks. Servers are saved in ~/Documents/Cline/MCP so you can easily share tools with friends!

Saoud Rizwan

61,730 次观看 • 1 年前

New LFM2.5-2.6B hits DeepSeek-V4 level on tool calling and runs 3.7x faster! We ran Liquid AI 's new LFM2.5-2.6B against DeepSeek-V4-Flash on one box with 4x RTX 5090. Both got the same three jobs, and each one only completes if the model fires every tool call Topics: -weather and local time in six cities -one budget into six currencies -four hotels checked and booked for one date Outputs: LFM2.5-2.6B: 35/35 tool-calls, 366 tok/s, 19s DeepSeek-V4-Flash: 35/35 tool-calls, 77 tok/s, 70s Both models made all 35 calls, and both fired twelve of them in one turn. LFM was trained for agents, and tool calling is where that shows. Strong result for a model you can run right on your phone

New LFM2.5-2.6B hits DeepSeek-V4 level on tool calling and runs 3.7x faster! We ran Liquid AI 's new LFM2.5-2.6B against DeepSeek-V4-Flash on one box with 4x RTX 5090. Both got the same three jobs, and each one only completes if the model fires every tool call Topics: -weather and local time in six cities -one budget into six currencies -four hotels checked and booked for one date Outputs: LFM2.5-2.6B: 35/35 tool-calls, 366 tok/s, 19s DeepSeek-V4-Flash: 35/35 tool-calls, 77 tok/s, 70s Both models made all 35 calls, and both fired twelve of them in one turn. LFM was trained for agents, and tool calling is where that shows. Strong result for a model you can run right on your phone

atomic.chat

112,171 次观看 • 17 天前

🔮 MCP INTEGRATION NOW LIVE ON OPENSERV This is bigger than most realize. We're not just adding a feature - we're enabling a fundamentally new paradigm for agent infrastructure. Before MCP: agents trapped in walled gardens, limited by what you explicitly feed them. After MCP: agents that can access 10K+ tools, interact with your existing systems, and truly operate in your digital world. Think about this: -Every integration used to require custom code -Every data source needed specific formatting -Every agent had to be built for specific tools MCP eliminates all of that. One standard to connect any agent to any tool. This isn't just convenience - it's the unlock that makes agents actually useful in the real world. OpenServ + MCP = AI teams that can genuinely get things done, not just talk about doing them. This is the breakthrough that turns agents from toys into tools.

🔮 MCP INTEGRATION NOW LIVE ON OPENSERV This is bigger than most realize. We're not just adding a feature - we're enabling a fundamentally new paradigm for agent infrastructure. Before MCP: agents trapped in walled gardens, limited by what you explicitly feed them. After MCP: agents that can access 10K+ tools, interact with your existing systems, and truly operate in your digital world. Think about this: -Every integration used to require custom code -Every data source needed specific formatting -Every agent had to be built for specific tools MCP eliminates all of that. One standard to connect any agent to any tool. This isn't just convenience - it's the unlock that makes agents actually useful in the real world. OpenServ + MCP = AI teams that can genuinely get things done, not just talk about doing them. This is the breakthrough that turns agents from toys into tools.

OpenServ

34,665 次观看 • 1 年前

LFM2-Audio just dropped! It's a 1.5B model that understands and generates both text and audio Inference 10x faster + quality on par with models 10x larger Available today on Hugging Face and our playground 🥳

LFM2-Audio just dropped! It's a 1.5B model that understands and generates both text and audio Inference 10x faster + quality on par with models 10x larger Available today on Hugging Face and our playground 🥳

Maxime Labonne

85,053 次观看 • 10 个月前