Loading video...

Video Failed to Load

Go Home

Recently, PostTrainBench showed how well AI agents can post-train models. Meta Harness showed that the harness itself can improve. What happens if a harness is improvising itself and the improvised harness is post training language models, all in a loop? Viv on this:

himanshustwts's profile picture

himanshu

27,135 subscribers

29,325 views • 2 months ago •via X (Twitter)

EducationNews & PoliticsScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

What the Lord Showed Me About Ai "Don't embrace it, harness it" Full video:
3:27

What the Lord Showed Me About Ai "Don't embrace it, harness it" Full video:

Brandon Biggs

12,094 views • 6 months ago

Ex-Google engineer explained AI agent loops, harness, evals in 20 minutes - better than 500$ courses. trace every run → judge it with an LLM → diagnose → fix → ship. That loop is how agents self-improve over time. Agent loops + memory + harness + evals - thats the stack. Watch it, then save the framework below.
19:30

Ex-Google engineer explained AI agent loops, harness, evals in 20 minutes - better than 500$ courses. trace every run → judge it with an LLM → diagnose → fix → ship. That loop is how agents self-improve over time. Agent loops + memory + harness + evals - thats the stack. Watch it, then save the framework below.

Movez

552,568 views • 14 days ago

🎉Introducing PyFlue: The Python-Native Agent Harness Framework.🧰 💡Flue for Python: Fred K. Schott fks CEO of HTML has launched Flue: The Agent Harness Framework for TypeScript. It brings programmable harness right into your agents rather than DIY plumbing. Python ecosystem already has 🦾 powerful AI/ML tools and frameworks and research initiatives but most frameworks asked users to build your own harness. Superagentic AI bringing this concept of Flue to Python 🐍 ecosystem. Here is PyFlue even even better 🤖 Agent = Model 💻 + Harness 🧰 + Memory 🧠 Almost all the feature of Flue plugged with LangChain Deepagents harness built by Harrison Chase and team Viv Sydney Runkle and more coming soon. 👉 Stop building agent loops, start using a harness. 💻 Try PyFlue Now : ⭐️ GitHub: 📚Docs: 📙 Blog Post: #HarnessEngineering #AgentHarnesses
0:39

🎉Introducing PyFlue: The Python-Native Agent Harness Framework.🧰 💡Flue for Python: Fred K. Schott fks CEO of HTML has launched Flue: The Agent Harness Framework for TypeScript. It brings programmable harness right into your agents rather than DIY plumbing. Python ecosystem already has 🦾 powerful AI/ML tools and frameworks and research initiatives but most frameworks asked users to build your own harness. Superagentic AI bringing this concept of Flue to Python 🐍 ecosystem. Here is PyFlue even even better 🤖 Agent = Model 💻 + Harness 🧰 + Memory 🧠 Almost all the feature of Flue plugged with LangChain Deepagents harness built by Harrison Chase and team Viv Sydney Runkle and more coming soon. 👉 Stop building agent loops, start using a harness. 💻 Try PyFlue Now : ⭐️ GitHub: 📚Docs: 📙 Blog Post: #HarnessEngineering #AgentHarnesses

Shashi 🇬🇧🇺🇸

69,688 views • 2 months ago

How to harness your body's innate ability to heal itself.
0:55

How to harness your body's innate ability to heal itself.

Red Pill Dispenser

108,751 views • 10 months ago

We're excited to introduce Claude Code, Cursor, and Codex agents in Mastra. Starting today, Mastra is now a meta-harness:
0:32

We're excited to introduce Claude Code, Cursor, and Codex agents in Mastra. Starting today, Mastra is now a meta-harness:

Sam Bhagwat

57,653 views • 27 days ago

Excited to release PostTrainBench v1.0! This benchmark evaluates the ability of frontier AI agents to post-train language models in a simplified setting. We believe this is a first step toward tracking progress in recursive self-improvement 🧵:
0:44

Excited to release PostTrainBench v1.0! This benchmark evaluates the ability of frontier AI agents to post-train language models in a simplified setting. We believe this is a first step toward tracking progress in recursive self-improvement 🧵:

Karina

182,596 views • 4 months ago

The Kardashev Scale is one of the coolest ways to think about how advanced a civilization really is Here is the cool visualization from The Kardashev Scale: - Type 1: Harness all the energy on a planet - Type 2: Harness all the energy from a star - Type 3: Harness all the energy in a galaxy The Kardashev Scale is not just sci-fi. It shows us the long-term destiny of intelligent life…if we don’t destroy ourselves first
0:34

The Kardashev Scale is one of the coolest ways to think about how advanced a civilization really is Here is the cool visualization from The Kardashev Scale: - Type 1: Harness all the energy on a planet - Type 2: Harness all the energy from a star - Type 3: Harness all the energy in a galaxy The Kardashev Scale is not just sci-fi. It shows us the long-term destiny of intelligent life…if we don’t destroy ourselves first

X Freeze

786,176 views • 3 months ago

Claude Code and Cursor... but they improve themselves. Autonomously. Meta Harness is wild. Had to make a video about it...
25:51

Claude Code and Cursor... but they improve themselves. Autonomously. Meta Harness is wild. Had to make a video about it...

Matthew Berman

152,514 views • 3 months ago

The entire AI industry is racing to build the smartest model. Satya Nadella just admitted that is not where the money is. The model is not the product. The harness is. That is the exact line. And it changes what Microsoft is actually competing on. OpenAI, Anthropic, Google, xAI, Meta every frontier lab is pouring hundreds of billions into training compute, chasing the next capability jump. Each betting that raw model intelligence is the moat. Microsoft is doing the opposite. It is building the harness the orchestration layer that sits above the model, connecting it to tools, data, permissions, sub-agents, and enterprise workflows. And it is letting OpenAI, Anthropic, and MAI compete to plug into it. "You need the model. But the model is not the product. The harness is." So do the math on what a harness actually does. A raw model dropped into an enterprise answers questions. That is a chatbot. A harness turns that same model into an agent that reads the SharePoint, edits the ERP entry, pulls the GitHub PR, updates Salesforce, and files the Excel report with the right permissions, the right audit trail, and the right sub-agent for each sub-task. The model provides the intelligence. The harness converts intelligence into work. Now here's where it gets interesting. "Even the best model in the world will feel broken without a great harness. And an okay model with a great harness can feel like magic." If that is true, the enterprise buyer is not buying model quality. The enterprise buyer is buying the harness. Which means model quality becomes a commodity input over time, and harness quality becomes the sustainable moat. Compare that to the strategy the entire frontier lab industry is executing. Everyone else is chasing the numerator raw intelligence. Almost nobody at scale is racing to build the denominator the orchestration layer that determines whether that intelligence can actually be deployed profitably inside a real company. The frontier model race has a 10 to 20 percent chance of producing a single dominant winner. Nadella just told the industry he does not need to be that winner. If OpenAI wins, Microsoft wins. If Anthropic wins, Microsoft wins. If MAI wins, Microsoft wins. If someone Microsoft has never heard of trains a better model in 2027, Microsoft still wins. Because the compute they train on, the harness they get plugged into, the enterprise contracts they get delivered through, and the products they sit inside are all Microsoft. He is not building the best AI model. He is building the layer that the best AI model has to run on to make anyone money. I wonder which position looks more valuable in ten years.
3:19

The entire AI industry is racing to build the smartest model. Satya Nadella just admitted that is not where the money is. The model is not the product. The harness is. That is the exact line. And it changes what Microsoft is actually competing on. OpenAI, Anthropic, Google, xAI, Meta every frontier lab is pouring hundreds of billions into training compute, chasing the next capability jump. Each betting that raw model intelligence is the moat. Microsoft is doing the opposite. It is building the harness the orchestration layer that sits above the model, connecting it to tools, data, permissions, sub-agents, and enterprise workflows. And it is letting OpenAI, Anthropic, and MAI compete to plug into it. "You need the model. But the model is not the product. The harness is." So do the math on what a harness actually does. A raw model dropped into an enterprise answers questions. That is a chatbot. A harness turns that same model into an agent that reads the SharePoint, edits the ERP entry, pulls the GitHub PR, updates Salesforce, and files the Excel report with the right permissions, the right audit trail, and the right sub-agent for each sub-task. The model provides the intelligence. The harness converts intelligence into work. Now here's where it gets interesting. "Even the best model in the world will feel broken without a great harness. And an okay model with a great harness can feel like magic." If that is true, the enterprise buyer is not buying model quality. The enterprise buyer is buying the harness. Which means model quality becomes a commodity input over time, and harness quality becomes the sustainable moat. Compare that to the strategy the entire frontier lab industry is executing. Everyone else is chasing the numerator raw intelligence. Almost nobody at scale is racing to build the denominator the orchestration layer that determines whether that intelligence can actually be deployed profitably inside a real company. The frontier model race has a 10 to 20 percent chance of producing a single dominant winner. Nadella just told the industry he does not need to be that winner. If OpenAI wins, Microsoft wins. If Anthropic wins, Microsoft wins. If MAI wins, Microsoft wins. If someone Microsoft has never heard of trains a better model in 2027, Microsoft still wins. Because the compute they train on, the harness they get plugged into, the enterprise contracts they get delivered through, and the products they sit inside are all Microsoft. He is not building the best AI model. He is building the layer that the best AI model has to run on to make anyone money. I wonder which position looks more valuable in ten years.

Vikram M

21,463 views • 7 days ago

With the Agents SDK and Vercel Sandbox, agents can execute work in isolated environments while keeping credentials separate from the harness.
1:02

With the Agents SDK and Vercel Sandbox, agents can execute work in isolated environments while keeping credentials separate from the harness.

OpenAI Developers

49,570 views • 2 months ago

Memory on the harness level after 2 years... i've started writing blogs again! In this post, I dive _very_ deep into the different ways to compose and add memory to the harness for various different use cases. it's interactive. it's fun. you can listen to it too!
0:33

Memory on the harness level after 2 years... i've started writing blogs again! In this post, I dive _very_ deep into the different ways to compose and add memory to the harness for various different use cases. it's interactive. it's fun. you can listen to it too!

Dhravya Shah

20,621 views • 19 days ago

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas
3:27

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

Rohan Paul

119,783 views • 20 days ago

Fireworks AI is now live on EvoSkill v1.3.0! You can now use Fireworks AI directly with EvoSkill to run fast inference on open models as both the evolution harness backend and the LLM scorer. Alongside Claude API and OpenRouter, Fireworks AI is now a first-class provider in EvoSkill.
0:21

Fireworks AI is now live on EvoSkill v1.3.0! You can now use Fireworks AI directly with EvoSkill to run fast inference on open models as both the evolution harness backend and the LLM scorer. Alongside Claude API and OpenRouter, Fireworks AI is now a first-class provider in EvoSkill.

Sentient

39,445 views • 16 days ago

The U.S.-Africa Leaders Summit only proved the enormous potential that our nations can harness together. The United States is all in on Africa’s future.
0:51

The U.S.-Africa Leaders Summit only proved the enormous potential that our nations can harness together. The United States is all in on Africa’s future.

President Biden Archived

1,045,542 views • 3 years ago

Well…Our First Attempts At Harness Training Went Well…As You Can See…Romeo O Romeo SORRY!!!!
0:24

Well…Our First Attempts At Harness Training Went Well…As You Can See…Romeo O Romeo SORRY!!!!

David Coverdale

12,512 views • 10 months ago

We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor. Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products.
0:35

We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor. Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products.

Cursor

3,039,737 views • 2 months ago

Here's all the different ways you can harness The Immortal's unending rage.
0:54

Here's all the different ways you can harness The Immortal's unending rage.

Invincible VS

39,484 views • 17 days ago

🚨ELON MUSK: "The biggest source of energy is The Sun. One of the ways you can think about the progress of a civilization is the Kardashev scale. You're Kardashev level 1 if you harness the power of a planet, 2 if you harness the power of a solar system, or 3 if you harness the power of a galaxy. When you think in terms of the Kardashev scale, it becomes obvious that the Sun is the most overwhelming source of energy, and everything else is tiny potatoes. The sun is a big potato. A humungous potato." 🥔☀️
1:22

🚨ELON MUSK: "The biggest source of energy is The Sun. One of the ways you can think about the progress of a civilization is the Kardashev scale. You're Kardashev level 1 if you harness the power of a planet, 2 if you harness the power of a solar system, or 3 if you harness the power of a galaxy. When you think in terms of the Kardashev scale, it becomes obvious that the Sun is the most overwhelming source of energy, and everything else is tiny potatoes. The sun is a big potato. A humungous potato." 🥔☀️

Autism Capital 🧩

17,687,192 views • 1 year ago

cat harness training
1:01

cat harness training

We don't deserve cats 😺

451,010 views • 10 months ago

this is huge news from Cursor, they've pulled of the impossible and turned their ai-wrapper into a in-destructible moat sam altman literally called it cursor's ai agent harness is available for anyone to build on, which means ai models are now a commodity > 1-time install and now anyone can run cursor's agent locally or via cloud. use any model (e.g. gpt 5.5) but with the added cursor harness that makes it 10X better. > its so good that 3 of cursors biggest competitors are embedding it into their products. > now cursor DOESN'T DEPEND on anthropic or openai. their own model (composer 2) competes directly! yesterday sam altman said the ai model and harness are one and the same and today cursor turned their harness into a self-owned moat fucking masterclass (coming from a former cursor / ai wrapper hater)
0:35

this is huge news from Cursor, they've pulled of the impossible and turned their ai-wrapper into a in-destructible moat sam altman literally called it cursor's ai agent harness is available for anyone to build on, which means ai models are now a commodity > 1-time install and now anyone can run cursor's agent locally or via cloud. use any model (e.g. gpt 5.5) but with the added cursor harness that makes it 10X better. > its so good that 3 of cursors biggest competitors are embedding it into their products. > now cursor DOESN'T DEPEND on anthropic or openai. their own model (composer 2) competes directly! yesterday sam altman said the ai model and harness are one and the same and today cursor turned their harness into a self-owned moat fucking masterclass (coming from a former cursor / ai wrapper hater)

Ejaaz

949,736 views • 2 months ago