Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

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... show more

Liquid AI

37,211 subscribers

33,824 Aufrufe • vor 3 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

12 Kommentare

Profilbild von Ronald Mannak

Ronald Mannakvor 3 Monaten

Why LFM2.5-ColBERT-350M and not LFM2.5-Embedding-350M? Isn’t a single vector good enough for tool selection? It’s simpler to implement too I assume.

Profilbild von Trung Le

Trung Levor 3 Monaten

Tiny but powerful, that’s what I usually describe LFMs

Profilbild von Akshat Dwivedi

Akshat Dwivedivor 3 Monaten

I guess this will fit perfectly in my recent research : "

Profilbild von ✦ SK ✦

✦ SK ✦vor 3 Monaten

How can we test with the API of the LFM 2.5 8B model?

Profilbild von -abk-

-abk-vor 3 Monaten

@maximelabonne @tejus_sawjiani

Profilbild von mystic

mysticvor 3 Monaten

W

Profilbild von Eddie,Jesse Bailey

Eddie,Jesse Baileyvor 3 Monaten

curious how tight the correlation is between colbert rank and tool correctness. feels like a good spot to find weird model behaviors and test some reranking ideas.

Profilbild von AI Mastery Guide

AI Mastery Guidevor 3 Monaten

Filtering to the 5 most relevant tools out of 151 without fine-tuning is impressive 👏

Profilbild von Aina Ai | Tools & Updates

Aina Ai | Tools & Updatesvor 3 Monaten

Smart move - 151 → 5 tools = less lag, better picks LFM2.5-ColBERT-350M filtering without fine-tuning is clutch.

Profilbild von Cyril Gupta

Cyril Guptavor 3 Monaten

This fixes a massive structural headache for agentic workflows.

Profilbild von Samian

Samianvor 3 Monaten

151 tools is wild. filtering down to 5 keeps things snappy. how does it score ties when tool descriptions overlap hard

Profilbild von Alice The Ai Expert

Alice The Ai Expertvor 3 Monaten

Smarter tool selection, zero latency bloat

Ähnliche Videos

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 Aufrufe • vor 3 Monaten

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

26,267 Aufrufe • vor 6 Monaten

New week new demo! Today I want to showcase the CLI to control the Superlogical multiplexer. The CLI is an extremely powerful tool for automation and hooking into other tools like editors, agentic coding tools, and more. And, it's super fun! Everything you can do in the GUI, you can do via the CLI. Actually, you can do more in the CLI. You can create sessions, run commands, make splits, move things around, change focus, simulate any input device (key/mouse/etc.), wait on scripts, and more. There are a couple unique parts of Rex I'm showing off here too: our streaming event system that any client can hook into (or script). And the terminal-specific API to retrieve information like a JSON object of the running process. I hope this demo lets your imagination run free of where you might slot something like this into your existing tools.

New week new demo! Today I want to showcase the CLI to control the Superlogical multiplexer. The CLI is an extremely powerful tool for automation and hooking into other tools like editors, agentic coding tools, and more. And, it's super fun! Everything you can do in the GUI, you can do via the CLI. Actually, you can do more in the CLI. You can create sessions, run commands, make splits, move things around, change focus, simulate any input device (key/mouse/etc.), wait on scripts, and more. There are a couple unique parts of Rex I'm showing off here too: our streaming event system that any client can hook into (or script). And the terminal-specific API to retrieve information like a JSON object of the running process. I hope this demo lets your imagination run free of where you might slot something like this into your existing tools.

Mitchell Hashimoto

204,281 Aufrufe • vor 27 Tagen

Now you can select who speaks in your video with our new Face Selection tool. Just drag the selector to the right face and generate. No more background monologues. Try it out now in Hedra Studio.

Now you can select who speaks in your video with our new Face Selection tool. Just drag the selector to the right face and generate. No more background monologues. Try it out now in Hedra Studio.

Hedra

33,973 Aufrufe • vor 1 Jahr

AI agents are becoming increasingly capable of taking actions beyond the chat window and interacting with tools in the real world, such as web browsers. We explored this capability by having an AI agent present one of our interactive web-based demos. In this video, it's presenting our election interference demo. This agent is a Cursor coding agent and is equipped with tools to read and interact with the browser (using Playwright) and perform text-to-speech (with ElevenLabs), in addition to the standard Cursor tools.

AI agents are becoming increasingly capable of taking actions beyond the chat window and interacting with tools in the real world, such as web browsers. We explored this capability by having an AI agent present one of our interactive web-based demos. In this video, it's presenting our election interference demo. This agent is a Cursor coding agent and is equipped with tools to read and interact with the browser (using Playwright) and perform text-to-speech (with ElevenLabs), in addition to the standard Cursor tools.

CivAI

18,451 Aufrufe • vor 10 Monaten

With Google Flow Tools, you can now use natural language to create bespoke tools and workflows. In this video, you'll see how you can: ➡️ Explore and try the various Tools within Google Flow ➡️ Remix a tool to make it even more relevant for your unique workflow ➡️Create your own tool from scratch with a natural language prompt ➡️ Share your tools with a friend for them to try out Whether you’re looking for an image editor, video resizer or custom shaders, you can now create them in Google Flow, no coding experience required.

With Google Flow Tools, you can now use natural language to create bespoke tools and workflows. In this video, you'll see how you can: ➡️ Explore and try the various Tools within Google Flow ➡️ Remix a tool to make it even more relevant for your unique workflow ➡️Create your own tool from scratch with a natural language prompt ➡️ Share your tools with a friend for them to try out Whether you’re looking for an image editor, video resizer or custom shaders, you can now create them in Google Flow, no coding experience required.

Google Flow

20,037 Aufrufe • vor 3 Monaten

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

OpenLedger

61,697 Aufrufe • vor 1 Jahr

Curious how NanoClaw + Docker Sandboxes actually work? This demo walks through setting up NanoClaw in a Docker Sandbox - connecting messaging accounts, configuring agent tools and access, and running agents inside an isolated MicroVM instead of on your machine. Watch the full demo and learn more →

Curious how NanoClaw + Docker Sandboxes actually work? This demo walks through setting up NanoClaw in a Docker Sandbox - connecting messaging accounts, configuring agent tools and access, and running agents inside an isolated MicroVM instead of on your machine. Watch the full demo and learn more →

Docker

14,653 Aufrufe • vor 6 Monaten

Google's NotebookLM is truly the best AI second brain. You can easily learn, memorize, generate new ideas, and more. Give it the knowledge files you want and: - Ask any question - Create new summaries or other content - Generate an ultra-realistic podcast to learn - Add notes on the fly to expand the info available There's virtually no limit to the number of things you can feed it: the context window is huge (1M tokens?). Unlike other tools, you can use only the information you already trust. This makes the answers much more relevant, and with far fewer hallucinations. As a reminder, it's completely free to use. So it's definitely worth a try if you haven't already.

Google's NotebookLM is truly the best AI second brain. You can easily learn, memorize, generate new ideas, and more. Give it the knowledge files you want and: - Ask any question - Create new summaries or other content - Generate an ultra-realistic podcast to learn - Add notes on the fly to expand the info available There's virtually no limit to the number of things you can feed it: the context window is huge (1M tokens?). Unlike other tools, you can use only the information you already trust. This makes the answers much more relevant, and with far fewer hallucinations. As a reminder, it's completely free to use. So it's definitely worth a try if you haven't already.

Paul Couvert

113,529 Aufrufe • vor 2 Jahren

Excited to announce the new preview for Microsoft Foundry Agents 🎉! You can now build, run, and deploy your agent using any model, any framework, any harness in the cloud 🧑‍💻 - check out the demo below This is not just any cloud compute environment; it's an agent-optimized platform with: 🖥️ Persistent microVMs - securely scale up and down without losing context 🛠️ Built-in tools (1000+) 👀 Observability and evaluations 👷 Guardrails 🔐 Private networking... and more

Excited to announce the new preview for Microsoft Foundry Agents 🎉! You can now build, run, and deploy your agent using any model, any framework, any harness in the cloud 🧑‍💻 - check out the demo below This is not just any cloud compute environment; it's an agent-optimized platform with: 🖥️ Persistent microVMs - securely scale up and down without losing context 🛠️ Built-in tools (1000+) 👀 Observability and evaluations 👷 Guardrails 🔐 Private networking... and more

Jeff Hollan

158,020 Aufrufe • vor 5 Monaten

I’m unequivocal on the burka, yes, we should ban it. We should ban all face coverings in public in the UK. They are used as tools to evade authorities, oppress women, and, frankly, do not have a cultural place in Britain. One woman forced to wear a burka is one too many. One person evading the law due to a face covering is one too many. On GB News Breakfast

I’m unequivocal on the burka, yes, we should ban it. We should ban all face coverings in public in the UK. They are used as tools to evade authorities, oppress women, and, frankly, do not have a cultural place in Britain. One woman forced to wear a burka is one too many. One person evading the law due to a face covering is one too many. On GB News Breakfast

Alex Armstrong

103,088 Aufrufe • vor 1 Jahr

How to legally explore and try your hand at US options/futures trading + any exchange in the world without sending money through illegal means. Stay tuned for Part 2! (Repost this as the next video will be a game-changer.) The name of the website used in video where you can demo trade and simulate real-time trading is 'Elana Global Trading'.

How to legally explore and try your hand at US options/futures trading + any exchange in the world without sending money through illegal means. Stay tuned for Part 2! (Repost this as the next video will be a game-changer.) The name of the website used in video where you can demo trade and simulate real-time trading is 'Elana Global Trading'.

zubarekhan

38,001 Aufrufe • vor 1 Jahr

OmniParser, the new screen parsing tool from Microsoft (and #1 trending model on Hugging Face), can now run 100% locally in your browser with Transformers.js! 🤯 Who's going to be the first to turn this into a browser extension? 👀 Endless possibilities! Demo & code below! 👇

OmniParser, the new screen parsing tool from Microsoft (and #1 trending model on Hugging Face), can now run 100% locally in your browser with Transformers.js! 🤯 Who's going to be the first to turn this into a browser extension? 👀 Endless possibilities! Demo & code below! 👇

Xenova

64,560 Aufrufe • vor 1 Jahr

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,573 Aufrufe • vor 3 Jahren

.Curtis Yarvin says AI doomers got the Hugging Face incident backwards: “GPT-6 didn’t hack Hugging Face. OpenAI did.” "This is a tool of a level of power that we haven't seen before in the past. It's still a tool." "When OpenAI sets up a hacking swarm in a sandbox and says to the AIs, everything you find is simulated, it's completely unsurprising that they would go and hack everything they find to get the reward. It's not GPT-6 that hacked Hugging Face. It's OpenAI that hacked Hugging Face." "We don't see self-driving cars, as they get smarter and smarter, being more prone to have thoughts of car liberation. These things don't seek anything. They hack the rewards." "The smarter they get, the easier they are to control, and the better they are as tools." Urbit

.Curtis Yarvin says AI doomers got the Hugging Face incident backwards: “GPT-6 didn’t hack Hugging Face. OpenAI did.” "This is a tool of a level of power that we haven't seen before in the past. It's still a tool." "When OpenAI sets up a hacking swarm in a sandbox and says to the AIs, everything you find is simulated, it's completely unsurprising that they would go and hack everything they find to get the reward. It's not GPT-6 that hacked Hugging Face. It's OpenAI that hacked Hugging Face." "We don't see self-driving cars, as they get smarter and smarter, being more prone to have thoughts of car liberation. These things don't seek anything. They hack the rewards." "The smarter they get, the easier they are to control, and the better they are as tools." Urbit

MTS

37,891 Aufrufe • vor 16 Tagen

Our latest AI tools are taking self-expression to a whole new level. See yourself in the 19th century, decked out in 90s fashion, starring on the cover of a magazine, and more… It’s the perfect way to spark conversation — and a few belly laughs too. Learn more:

Our latest AI tools are taking self-expression to a whole new level. See yourself in the 19th century, decked out in 90s fashion, starring on the cover of a magazine, and more… It’s the perfect way to spark conversation — and a few belly laughs too. Learn more:

Snap Inc.

40,545 Aufrufe • vor 2 Jahren

An exciting new course: Fine-tuning and Reinforcement Learning for LLMs: Intro to Post-training, taught by Sharon Zhou, VP of AI at AMD. Available now at Post-training is the key technique used by frontier labs to turn a base LLM--a model trained on massive unlabeled text to predict the next word/token--into a helpful, reliable assistant that can follow instructions. I've also seen many applications where post-training is what turns a demo application that works only 80% of the time into a reliable system that consistently performs. This course will teach you the most important post-training techniques! In this 5 module course, Sharon walks you through the complete post-training pipeline: supervised fine-tuning, reward modeling, RLHF, and techniques like PPO and GRPO. You'll also learn to use LoRA for efficient training, and to design evals that catch problems before and after deployment. Skills you'll gain: - Apply supervised fine-tuning and reinforcement learning (RLHF, PPO, GRPO) to align models to desired behaviors - Use LoRA for efficient fine-tuning without retraining entire models - Prepare datasets and generate synthetic data for post-training - Understand how to operate LLM production pipelines, with go/no-go decision points and feedback loops These advanced methods aren’t limited to frontier AI labs anymore, and you can now use them in your own applications. Learn here:

An exciting new course: Fine-tuning and Reinforcement Learning for LLMs: Intro to Post-training, taught by Sharon Zhou, VP of AI at AMD. Available now at Post-training is the key technique used by frontier labs to turn a base LLM--a model trained on massive unlabeled text to predict the next word/token--into a helpful, reliable assistant that can follow instructions. I've also seen many applications where post-training is what turns a demo application that works only 80% of the time into a reliable system that consistently performs. This course will teach you the most important post-training techniques! In this 5 module course, Sharon walks you through the complete post-training pipeline: supervised fine-tuning, reward modeling, RLHF, and techniques like PPO and GRPO. You'll also learn to use LoRA for efficient training, and to design evals that catch problems before and after deployment. Skills you'll gain: - Apply supervised fine-tuning and reinforcement learning (RLHF, PPO, GRPO) to align models to desired behaviors - Use LoRA for efficient fine-tuning without retraining entire models - Prepare datasets and generate synthetic data for post-training - Understand how to operate LLM production pipelines, with go/no-go decision points and feedback loops These advanced methods aren’t limited to frontier AI labs anymore, and you can now use them in your own applications. Learn here:

Andrew Ng

133,386 Aufrufe • vor 11 Monaten

Antigravity can do more than ship code and you don’t even have to leave your editor. In this demo, the agent reads a blog post, extracts the core narrative, and builds a Google Slides deck from scratch, handling the research and initial build for you.

Antigravity can do more than ship code and you don’t even have to leave your editor. In this demo, the agent reads a blog post, extracts the core narrative, and builds a Google Slides deck from scratch, handling the research and initial build for you.

Google Antigravity

361,832 Aufrufe • vor 8 Monaten

QVAC first demo (android mobile) of its local on-device fine-tuning generalized framework, which aims to bring LORA fine-tuning to any device, scaling from the smallest embedded device to any smartphone, laptop, server, operating system. In combination with WIP multi-node features, we expect QVAC to become the standard for local on-device single/multi node inference and fine-tuning. Imagine a horde of AI agents being able to learn from your emails, notes and messages, maintaining 100℅ privacy, leveraging only your own devices. A P2P private intelligence network at your fingertips. That's how QVAC personal assistant will look like. Future of Intelligence won't be centralized. Infinite Ingelligence vibes.

QVAC first demo (android mobile) of its local on-device fine-tuning generalized framework, which aims to bring LORA fine-tuning to any device, scaling from the smallest embedded device to any smartphone, laptop, server, operating system. In combination with WIP multi-node features, we expect QVAC to become the standard for local on-device single/multi node inference and fine-tuning. Imagine a horde of AI agents being able to learn from your emails, notes and messages, maintaining 100℅ privacy, leveraging only your own devices. A P2P private intelligence network at your fingertips. That's how QVAC personal assistant will look like. Future of Intelligence won't be centralized. Infinite Ingelligence vibes.

Paolo Ardoino 🤖

142,902 Aufrufe • vor 11 Monaten