Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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

28,925 subscribers

18,403 views • 12 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Storing too many tools in your context window increases latency and can lead to wrong tool selection. In this demo, we used LFM2.5-ColBERT-350M as a filter to only select the five most relevant tools among 151 options. It's fast and reliable, even without any specific fine-tuning. Try the demo on Hugging Face! And learn more on our blog:

Storing too many tools in your context window increases latency and can lead to wrong tool selection. In this demo, we used LFM2.5-ColBERT-350M as a filter to only select the five most relevant tools among 151 options. It's fast and reliable, even without any specific fine-tuning. Try the demo on Hugging Face! And learn more on our blog:

Liquid AI

32,574 views • 11 days ago

Our new LFM2.5-350M brings tool calling and agentic AI to Raspberry Pi level hardware

Our new LFM2.5-350M brings tool calling and agentic AI to Raspberry Pi level hardware

Mathias Lechner

13,398 views • 3 months ago

NEW: LiquidAI just released LFM2.5-350M, a tiny model that brings agentic AI and tool-calling capabilities to resource-constrained environments. 🤯 It can even run locally in your browser via WebGPU, serving as a powerful companion while you browse the web. Try the demo! 👇

NEW: LiquidAI just released LFM2.5-350M, a tiny model that brings agentic AI and tool-calling capabilities to resource-constrained environments. 🤯 It can even run locally in your browser via WebGPU, serving as a powerful companion while you browse the web. Try the demo! 👇

Xenova

26,126 views • 3 months ago

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

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

96,781 views • 11 months ago

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

forloop

225,912 views • 4 months ago

🚀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

43,652 views • 8 months ago

Today we’re launching Prompt Adaptation, a state-of-the-art agentic system that automatically adapts prompts across LLMs. Prompt Adaptation outperforms all other methods and significantly improves accuracy over manual prompt engineering, saving you thousands of hours per year.

Today we’re launching Prompt Adaptation, a state-of-the-art agentic system that automatically adapts prompts across LLMs. Prompt Adaptation outperforms all other methods and significantly improves accuracy over manual prompt engineering, saving you thousands of hours per year.

Tomas Hernando Kofman

110,765 views • 1 year ago

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

91,142 views • 8 months ago

Peter Steinberger Quietly Started A Shift That Makes Claude 35x Cheaper To Run The way Claude Code talks to tools matters more than people think. Most use MCP, and it quietly eats tokens, it loads everything into context every time, even tools you never call. One benchmark: MCP burned 35x more tokens than a CLI on the same task. Peter Steinberger, the OpenClaw guy, got annoyed by this and started building lean CLIs himself. That kicked off a tool called Printing Press. You point Claude Code at any website, even ones with no API like ESPN or Craigslist, and it builds a small command tool for it in about 10 minutes. In one demo, a request pulled 132,000 tokens of raw data, but the tool processed it locally and only handed Claude a 2,000-token summary. The rest never touched the context window. It also comes with ~50 ready-made tools you can grab right away. To start, point Claude Code at the links from and ask it to set it up. Bookmark this.

Peter Steinberger Quietly Started A Shift That Makes Claude 35x Cheaper To Run The way Claude Code talks to tools matters more than people think. Most use MCP, and it quietly eats tokens, it loads everything into context every time, even tools you never call. One benchmark: MCP burned 35x more tokens than a CLI on the same task. Peter Steinberger, the OpenClaw guy, got annoyed by this and started building lean CLIs himself. That kicked off a tool called Printing Press. You point Claude Code at any website, even ones with no API like ESPN or Craigslist, and it builds a small command tool for it in about 10 minutes. In one demo, a request pulled 132,000 tokens of raw data, but the tool processed it locally and only handed Claude a 2,000-token summary. The rest never touched the context window. It also comes with ~50 ready-made tools you can grab right away. To start, point Claude Code at the links from and ask it to set it up. Bookmark this.

Ridark

32,351 views • 3 days ago

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:

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

95,849 views • 3 years ago

This simple looking tool has a surprisingly smart watch how a piece of raber and few welding tricks turn into a practical workshop invention that saves time and effort.

This simple looking tool has a surprisingly smart watch how a piece of raber and few welding tricks turn into a practical workshop invention that saves time and effort.

Economics and Agriculture

39,095 views • 29 days ago

TIPS: Besides 3D wallpaper, the latest XR Animator also improves the performance of some Transformers-based AI models. For example, object detection AI based on Transformers is slower but more accurate, and this update makes these models more usable💨

TIPS: Besides 3D wallpaper, the latest XR Animator also improves the performance of some Transformers-based AI models. For example, object detection AI based on Transformers is slower but more accurate, and this update makes these models more usable💨

Butz Yung

23,932 views • 7 months ago

The BIGGEST System Prompt LEAK and this is for Claude!! Claude’s entire system prompt literally leaked on GitHub and it’s 24,000 tokens long:

The BIGGEST System Prompt LEAK and this is for Claude!! Claude’s entire system prompt literally leaked on GitHub and it’s 24,000 tokens long:

Meera | AI Tools & News

24,809 views • 1 year ago

Launching AI Discovery And Communication DeepAgent discovers other AI agents and software tools on the fly and communicates with them to perform complex tasks. Here is how it works - - DeepAgent searches for other AI agents and tools - Finds the right tool for the job - Establishes contact using MCP and handles auth - Collaborates with the other tool to get the job done! - Remembers this tool for future colabs! Much like humans, it can create a team of AI agents or software tools to perform tasks. Here it is, learning about MindMaps, communicating with another server, and creating a Mindmap!!

Launching AI Discovery And Communication DeepAgent discovers other AI agents and software tools on the fly and communicates with them to perform complex tasks. Here is how it works - - DeepAgent searches for other AI agents and tools - Finds the right tool for the job - Establishes contact using MCP and handles auth - Collaborates with the other tool to get the job done! - Remembers this tool for future colabs! Much like humans, it can create a team of AI agents or software tools to perform tasks. Here it is, learning about MindMaps, communicating with another server, and creating a Mindmap!!

Bindu Reddy

13,598 views • 1 year ago

Michaël van de Poppe says 99% of tokens have no purpose and no value: "NEAR is one of the prime tokens we hold because of the revenue it generates and the growth rate it has." "You can model it for the coming years and build a fuel where the current price is underpriced based on market circumstances, not the token itself." "Even Aave. We hold it, but ecosystem events can still produce a drawdown. That's why allocations stay small and most of the fund runs default trading."

Michaël van de Poppe says 99% of tokens have no purpose and no value: "NEAR is one of the prime tokens we hold because of the revenue it generates and the growth rate it has." "You can model it for the coming years and build a fuel where the current price is underpriced based on market circumstances, not the token itself." "Even Aave. We hold it, but ecosystem events can still produce a drawdown. That's why allocations stay small and most of the fund runs default trading."

The Rollup

20,913 views • 1 month ago

Finally got a chance to play around with Andrej Karpathy's LLM Council. I built it as a plugin inside of Claude Code. Hooked it up with OpenRouter for models. The AskUserQuestion tool came in handy to select the council and chairman. This is my first test, but I agree with Karpathy that the concept of LLM ensembles can be used beyond models that offer perspectives on interesting questions. I feel like this could have really cool applications in agentic coding. More on that soon. I built this as a plugin, so next I will be exploring other user cases around agentic coding, like evaluation, tool building, designing, and research. If there is enough interest, I will clean it up and push it out as an open plugin.

Finally got a chance to play around with Andrej Karpathy's LLM Council. I built it as a plugin inside of Claude Code. Hooked it up with OpenRouter for models. The AskUserQuestion tool came in handy to select the council and chairman. This is my first test, but I agree with Karpathy that the concept of LLM ensembles can be used beyond models that offer perspectives on interesting questions. I feel like this could have really cool applications in agentic coding. More on that soon. I built this as a plugin, so next I will be exploring other user cases around agentic coding, like evaluation, tool building, designing, and research. If there is enough interest, I will clean it up and push it out as an open plugin.

elvis

79,648 views • 5 months ago

Build edge AI applications with Google tools using Hybrid LLMs. Learn how to combine the on-device capabilities of Gemma and cloud-based Gemini models for optimal performance and privacy.

Build edge AI applications with Google tools using Hybrid LLMs. Learn how to combine the on-device capabilities of Gemma and cloud-based Gemini models for optimal performance and privacy.

Google AI Developers

15,365 views • 1 year ago

MOST PEOPLE DON'T KNOW THIS "ID The Mike" works on Run Plays (and has for years) Don't believe me? Watch this video This is one of the biggest tools we have on Offense to prevent User Defenders from "Shooting The Gap" This could 10x your Run Game, please start doing it

MOST PEOPLE DON'T KNOW THIS "ID The Mike" works on Run Plays (and has for years) Don't believe me? Watch this video This is one of the biggest tools we have on Offense to prevent User Defenders from "Shooting The Gap" This could 10x your Run Game, please start doing it

Civ

16,628 views • 2 months ago

ever wonder what AI models and tools you can actually use for your work ? introducing the Creative Arena powered by @FAL and Contra Creative Arena is where creative professionals judge AI models and tools vs real client demand, not just speed or accuracy want to try it?

ever wonder what AI models and tools you can actually use for your work ? introducing the Creative Arena powered by @FAL and Contra Creative Arena is where creative professionals judge AI models and tools vs real client demand, not just speed or accuracy want to try it?

ben

868,125 views • 9 months ago

The £350m-a-week NHS lie defined Brexit. Farage promised it, voters believed it, and Britain is still waiting. Brexit's most famous pledge, £350m weekly for the NHS, was pure lie. The only thing that's grown is the size of the lie. #BBCBreakfast #BBCLauraK #r4today

The £350m-a-week NHS lie defined Brexit. Farage promised it, voters believed it, and Britain is still waiting. Brexit's most famous pledge, £350m weekly for the NHS, was pure lie. The only thing that's grown is the size of the lie. #BBCBreakfast #BBCLauraK #r4today

Sarah Attlee

83,142 views • 5 months ago