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。

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:

himanshu

27,135 subscribers

29,325 次观看 • 4 个月前 •via X (Twitter)

教育新闻政治科学技术

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

This is my favorite demo how useful a robot can be just with a good harness design + models co-trained with our harness. Tools given to the robot are 1) manipulation (via an action model) 2) locomotion 3) speeking to a person

This is my favorite demo how useful a robot can be just with a good harness design + models co-trained with our harness. Tools given to the robot are 1) manipulation (via an action model) 2) locomotion 3) speeking to a person

Kangwook Lee

21,840 次观看 • 20 天前

Anthropic engineer: "If you want to be in the top 1% of AI engineers, build a harness that improves itself Harnesses and graphs" In just 41 minutes, she explains how Anthropic builds with AI internally and why harnesses and graphs sit at the center of it Prompts → Agents → Harness → Loops → Graphs A harness makes each unit of work correct without you A graph decides which units should exist and turns every accepted result into a rule for the next run That's what "self-improving" actually means And it's the part almost nobody is building Watch it today Then save the full harness engineering guide below before everyone starts catching up ↓

Anthropic engineer: "If you want to be in the top 1% of AI engineers, build a harness that improves itself Harnesses and graphs" In just 41 minutes, she explains how Anthropic builds with AI internally and why harnesses and graphs sit at the center of it Prompts → Agents → Harness → Loops → Graphs A harness makes each unit of work correct without you A graph decides which units should exist and turns every accepted result into a rule for the next run That's what "self-improving" actually means And it's the part almost nobody is building Watch it today Then save the full harness engineering guide below before everyone starts catching up ↓

Lunar

16,448 次观看 • 7 天前

Everyone is saying “it’s the harness, not the model.” But...no one is really explaining what that means. I wanted to understand harness engineering better, so on today's episode of How I AI, I built my own: a custom harness using ClaudeDevs SDK to triage Sentry bugs, verify root cause, and ship fixes. The big unlock? Realizing a custom harness lets you stop micromanaging chats and get agents that do exactly what you want. Full tutorial now on YT:

Everyone is saying “it’s the harness, not the model.” But...no one is really explaining what that means. I wanted to understand harness engineering better, so on today's episode of How I AI, I built my own: a custom harness using ClaudeDevs SDK to triage Sentry bugs, verify root cause, and ship fixes. The big unlock? Realizing a custom harness lets you stop micromanaging chats and get agents that do exactly what you want. Full tutorial now on YT:

claire vo 🖤

40,289 次观看 • 2 个月前

MIT PhD student Alex Zhang on why simple harness abstractions beat models trained around their own harness: "When these abstractions are implemented in a really simple way, basically what you see with Prime Agent is that you can slot in any model. We don't train any model around Prime Agent." "In a lot of cases, we see Prime Agent doing better than models trained around a certain harness. It's purely because these abstractions take advantage of the raw capabilities of the models." alex zhang Seth Karten Prime Intellect

MIT PhD student Alex Zhang on why simple harness abstractions beat models trained around their own harness: "When these abstractions are implemented in a really simple way, basically what you see with Prime Agent is that you can slot in any model. We don't train any model around Prime Agent." "In a lot of cases, we see Prime Agent doing better than models trained around a certain harness. It's purely because these abstractions take advantage of the raw capabilities of the models." alex zhang Seth Karten Prime Intellect

MTS

148,427 次观看 • 1 个月前

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.

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

565,706 次观看 • 2 个月前

This guy explained agent harness, memory, and loop engineering in one video - clearer than most paid courses a raw LLM with no harness is a wild horse. all power, no direction > trace the run -> score it with an LLM -> diagnose the bottleneck -> patch it -> ship it that loop is what lets an agent get sharper on its own, run after run memory + harness + loop engineering + evals - that's the whole stack in one picture watch it, then grab the diagram below

This guy explained agent harness, memory, and loop engineering in one video - clearer than most paid courses a raw LLM with no harness is a wild horse. all power, no direction > trace the run -> score it with an LLM -> diagnose the bottleneck -> patch it -> ship it that loop is what lets an agent get sharper on its own, run after run memory + harness + loop engineering + evals - that's the whole stack in one picture watch it, then grab the diagram below

Mr. Buzzoni

45,093 次观看 • 1 个月前

🎉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

🎉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

69,884 次观看 • 4 个月前

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 🧵:

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

195,781 次观看 • 6 个月前

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

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

786,793 次观看 • 5 个月前

OpenAI engineer: "Nobody on my team has touched code in 9 months. Agents write all the code, the way you do it is harness engineering." In 45 minutes he breaks down exactly how to build the setup so agents do the full job without you in the loop. This beats any paid course on building agents I've seen. Watch it, then read the full guide on harness engineering below.

OpenAI engineer: "Nobody on my team has touched code in 9 months. Agents write all the code, the way you do it is harness engineering." In 45 minutes he breaks down exactly how to build the setup so agents do the full job without you in the loop. This beats any paid course on building agents I've seen. Watch it, then read the full guide on harness engineering below.

Anatoli Kopadze

25,222 次观看 • 1 个月前

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.

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 次观看 • 2 个月前

MOST PEOPLE BUILD AI AGENTS BACKWARDS. They start with prompts, then add tools, memory, subagents, dashboards, and a graph nobody can debug. Then they wonder why the agent is expensive, confused, and unreliable. The better order is simple: harness first loop second graph only when needed A harness gives the model a workspace, tools, permissions, logs, and a definition of done. A loop lets it try, fail, read feedback, repair, and stop. A graph only makes sense when the workflow branches: approvals, parallel work, durable state, different routes, restart recovery. A graph is not a smarter prompt. A loop is not a production system. A harness is not just a system prompt. Most agents do not fail because the model is weak. They fail because nobody defined what success means.

MOST PEOPLE BUILD AI AGENTS BACKWARDS. They start with prompts, then add tools, memory, subagents, dashboards, and a graph nobody can debug. Then they wonder why the agent is expensive, confused, and unreliable. The better order is simple: harness first loop second graph only when needed A harness gives the model a workspace, tools, permissions, logs, and a definition of done. A loop lets it try, fail, read feedback, repair, and stop. A graph only makes sense when the workflow branches: approvals, parallel work, durable state, different routes, restart recovery. A graph is not a smarter prompt. A loop is not a production system. A harness is not just a system prompt. Most agents do not fail because the model is weak. They fail because nobody defined what success means.

Fluixo

11,303 次观看 • 1 个月前

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!

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

20,951 次观看 • 2 个月前

Fireworks AI is now live on EvoSkill v1.3.0! You can now use Fireworks 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.

Fireworks AI is now live on EvoSkill v1.3.0! You can now use Fireworks 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

40,335 次观看 • 2 个月前

"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

"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

120,488 次观看 • 2 个月前

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.

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

1,045,634 次观看 • 3 年前

Anthropic Technical Staff Jess Yan says the harness and the model cannot be pulled apart without giving up performance, though she flags her own bias. "I think I am quite biased but I also think that it is impossible to get the maximum possible performance without tying together the harness and the model." "Now the components of the harness and maybe the thickness of the harness will change over time as models get more and more capable." "However, when we test our models and when we are assessing their performance we always have to test it in conjunction with a harness." "And are we going to test it with all the different harnesses of the world? We're going to select the harnesses that we have built." "And so there is an aspect of the necessity of building models is that you have to be testing them with harnesses, and that sort of keeps them paired together."

Anthropic Technical Staff Jess Yan says the harness and the model cannot be pulled apart without giving up performance, though she flags her own bias. "I think I am quite biased but I also think that it is impossible to get the maximum possible performance without tying together the harness and the model." "Now the components of the harness and maybe the thickness of the harness will change over time as models get more and more capable." "However, when we test our models and when we are assessing their performance we always have to test it in conjunction with a harness." "And are we going to test it with all the different harnesses of the world? We're going to select the harnesses that we have built." "And so there is an aspect of the necessity of building models is that you have to be testing them with harnesses, and that sort of keeps them paired together."

Fireside Alpha

584,074 次观看 • 1 个月前

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.

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

3,051,896 次观看 • 4 个月前

🚨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." 🥔☀️

🚨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 🧩

17,688,100 次观看 • 1 年前

GPT-Live-1 is now available in the API. Bring ChatGPT’s natural back-and-forth to your app, with voice agents that listen while they speak and work with the models and harness you choose.

GPT-Live-1 is now available in the API. Bring ChatGPT’s natural back-and-forth to your app, with voice agents that listen while they speak and work with the models and harness you choose.

OpenAI Developers

5,380,615 次观看 • 23 小时前