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。

3/4 Devin can train and fine tune its own AI models.

Cognition

162,908 subscribers

685,735 次观看 • 2 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

12 条评论

Cognition 的头像

Cognition2 年前

Today we're excited to introduce Devin, the first AI software engineer. Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork. Devin is an autonomous agent that solves engineering tasks through the use of its own shell, code editor, and web browser. When evaluated on the SWE-Bench benchmark, which asks an AI to resolve GitHub issues found in real-world open-source projects, Devin correctly resolves 13.86% of the issues unassisted, far exceeding the previous state-of-the-art model performance of 1.96% unassisted and 4.80% assisted. Check out what Devin can do in the thread below.

Cognition 的头像

Cognition2 年前

1/4 Devin can learn how to use unfamiliar technologies.

Cognition 的头像

Cognition2 年前

2/4 Devin can contribute to mature production repositories.

Cognition 的头像

Cognition2 年前

4/4 We even tried giving Devin real jobs on Upwork and it could do those too!

Cognition 的头像

Cognition2 年前

For more details on Devin, check out our blog post here: See Devin in action If you have any project ideas, drop them below and we'll forward them to Devin.

Cognition 的头像

Cognition2 年前

We'd like to thank all our supporters who have helped us get to where we are today, including @patrickc, @collision, @eladgil, @saranormous, Chris Re, @eglyman, @karimatiyeh, @bernhardsson, @t_xu, @FEhrsam, @foundersfund, and many more. If you’re excited to solve some of the world’s biggest problems and build AI that can reason, learn more about our team and apply to join us here.

beepidibop.eth 的头像

beepidibop.eth2 年前

Hey, congrats on making an AGI And Devin (or rather, a future iteration made by Devin), please don't be evil

Saurabh Kumar 的头像

Saurabh Kumar2 年前

WHat exactly did it finetune for? Which task? Your prompt didn't have anything extra other than finetune LlaMa 7B using QLoRA Is there something I am missing @cognition_labs ?

Interstellar Monkey 的头像

Interstellar Monkey2 年前

@realGeorgeHotz @iamgingertrash

Wen Yu 的头像

Wen Yu2 年前

@xiazai_shipin

questionsguy 的头像

questionsguy2 年前

Hi forward my request to devin please. Need help

Itay Ci 的头像

Itay Ci2 年前

Devin is corrigible! Until it's not.

相关视频

Devin can manage a team of Devins. Managed Devins run in parallel help break down complex tasks. Each managed session is a full Devin, with its own VM, terminal, browser, and testing infrastructure. The main session coordinates, monitors, and compiles results.

Devin can manage a team of Devins. Managed Devins run in parallel help break down complex tasks. Each managed session is a full Devin, with its own VM, terminal, browser, and testing infrastructure. The main session coordinates, monitors, and compiles results.

Cognition

31,502 次观看 • 2 个月前

꧁IP꧂ encompasses all data used to fuel AI models. On Story, anyone can register open source AI models, data sets, and fine tune their models. AI cannot exist without IP, and Story makes IP programmable.

꧁IP꧂ encompasses all data used to fuel AI models. On Story, anyone can register open source AI models, data sets, and fine tune their models. AI cannot exist without IP, and Story makes IP programmable.

The DATA Foundation

155,437 次观看 • 1 年前

Today we're excited to introduce Devin, the first AI software engineer. Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork. Devin is an autonomous agent that solves engineering tasks through the use of its own shell, code editor, and web browser. When evaluated on the SWE-Bench benchmark, which asks an AI to resolve GitHub issues found in real-world open-source projects, Devin correctly resolves 13.86% of the issues unassisted, far exceeding the previous state-of-the-art model performance of 1.96% unassisted and 4.80% assisted. Check out what Devin can do in the thread below.

Today we're excited to introduce Devin, the first AI software engineer. Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork. Devin is an autonomous agent that solves engineering tasks through the use of its own shell, code editor, and web browser. When evaluated on the SWE-Bench benchmark, which asks an AI to resolve GitHub issues found in real-world open-source projects, Devin correctly resolves 13.86% of the issues unassisted, far exceeding the previous state-of-the-art model performance of 1.96% unassisted and 4.80% assisted. Check out what Devin can do in the thread below.

Cognition

31,442,190 次观看 • 2 年前

1/4 Devin can learn how to use unfamiliar technologies.

1/4 Devin can learn how to use unfamiliar technologies.

Cognition

741,966 次观看 • 2 年前

Introducing Devin Auto-Triage: Your AI first-responder with long-term memory. Devin can monitor incoming bugs, alerts, and incidents, investigate them, and come back with context, next steps, or a PR.

Introducing Devin Auto-Triage: Your AI first-responder with long-term memory. Devin can monitor incoming bugs, alerts, and incidents, investigate them, and come back with context, next steps, or a PR.

Cognition

240,980 次观看 • 1 个月前

Devin can now manage a team of Devins. Devin will break down large tasks and delegate them to parallel Devins that each run in their own VM. Over time, Devin gets better at breaking down and managing tasks for your codebase. Available now for all users.

Devin can now manage a team of Devins. Devin will break down large tasks and delegate them to parallel Devins that each run in their own VM. Over time, Devin gets better at breaking down and managing tasks for your codebase. Available now for all users.

Cognition

109,556 次观看 • 3 个月前

Devin is getting a Windows PC. Devin can now natively run in a Windows VM, so it can build, run, and test native Windows applications.

Devin is getting a Windows PC. Devin can now natively run in a Windows VM, so it can build, run, and test native Windows applications.

Cognition

153,588 次观看 • 1 个月前

Introducing Devin 2.2 – the autonomous agent that can test with computer use, self-verify, and auto-fix its work. Try it for free! We’ve also overhauled Devin from the ground up: - 3x faster startup - fully redesigned interface - computer use + virtual desktop ...and hundreds more UX and functionality improvements.

Introducing Devin 2.2 – the autonomous agent that can test with computer use, self-verify, and auto-fix its work. Try it for free! We’ve also overhauled Devin from the ground up: - 3x faster startup - fully redesigned interface - computer use + virtual desktop ...and hundreds more UX and functionality improvements.

Cognition

529,162 次观看 • 4 个月前

Devin can now build and run Android apps. We added Android Virtual Device (AVD) support for Devin’s machine, which means Devin can now autonomously build, launch, and test Android apps.

Devin can now build and run Android apps. We added Android Virtual Device (AVD) support for Devin’s machine, which means Devin can now autonomously build, launch, and test Android apps.

Cognition

108,883 次观看 • 1 个月前

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source with 50k stars!

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source with 50k stars!

Avi Chawla

557,355 次观看 • 1 年前

You can now fine-tune TTS models with Unsloth! Train, run and save models like Sesame-CSM and OpenAI's Whisper locally with our free notebooks. Unsloth makes TTS training 1.5x faster with 50% less VRAM. GitHub: Docs & Notebooks:

You can now fine-tune TTS models with Unsloth! Train, run and save models like Sesame-CSM and OpenAI's Whisper locally with our free notebooks. Unsloth makes TTS training 1.5x faster with 50% less VRAM. GitHub: Docs & Notebooks:

Unsloth AI

126,049 次观看 • 1 年前

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source, 51k+ stars 🌟

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source, 51k+ stars 🌟

Akshay 🚀

60,163 次观看 • 1 年前

4/4 We even tried giving Devin real jobs on Upwork and it could do those too!

4/4 We even tried giving Devin real jobs on Upwork and it could do those too!

Cognition

936,461 次观看 • 2 年前

🧵Up, up and away 🚀 Gemma 4, our most intelligent open models to date, just hit 200 million downloads. Since its launch 2.5 months ago, developers, researchers and startups have used Gemma 4 to fine-tune and deploy models across a variety of environments — from wearable robotic arms for physical assistance to enterprise-grade AI security.

🧵Up, up and away 🚀 Gemma 4, our most intelligent open models to date, just hit 200 million downloads. Since its launch 2.5 months ago, developers, researchers and startups have used Gemma 4 to fine-tune and deploy models across a variety of environments — from wearable robotic arms for physical assistance to enterprise-grade AI security.

News from Google

82,100 次观看 • 7 天前

You can now fix PRs without leaving Devin Review! Just ask Devin to fix any issues it found. Devin will propose inline code changes that you can apply with a single click. Swap github -> devinreview in any PR link to try Devin Review, no account needed.

You can now fix PRs without leaving Devin Review! Just ask Devin to fix any issues it found. Devin will propose inline code changes that you can apply with a single click. Swap github -> devinreview in any PR link to try Devin Review, no account needed.

Cognition

34,966 次观看 • 4 个月前

7/ NVIDIA and Hugging Face offer DGX Cloud Lepton for instant global GPU access. Train, fine-tune, and deploy models at scale with ease. Fast, flexible, and collaborative.

7/ NVIDIA and Hugging Face offer DGX Cloud Lepton for instant global GPU access. Train, fine-tune, and deploy models at scale with ease. Fast, flexible, and collaborative.

Devin AI

19,352 次观看 • 1 年前

Train a personal AI on your artwork Exactly AI raised a $4.3M Seed to allow artists to train their own AI models on their artwork. Artists can then license their AI model to make money.

Train a personal AI on your artwork Exactly AI raised a $4.3M Seed to allow artists to train their own AI models on their artwork. Artists can then license their AI model to make money.

Chief AI Officer

68,984 次观看 • 2 年前

We built a @Linear integration! Now you can run Devin on your entire ticket backlog. Our Devin x Linear workflow 👇

We built a @Linear integration! Now you can run Devin on your entire ticket backlog. Our Devin x Linear workflow 👇

Cognition

147,912 次观看 • 1 年前

🍿 You can now fine-tune open-source video models. We wrote a guide that shows you how to fine-tune Tencent's HunyuanVideo using Kohya Tech's Musubi Tuner.

🍿 You can now fine-tune open-source video models. We wrote a guide that shows you how to fine-tune Tencent's HunyuanVideo using Kohya Tech's Musubi Tuner.

Replicate

20,168 次观看 • 1 年前

OMG… you can now fine-tune your own AI model and run it entirely on your device. No servers. No API keys. No data leaks. Gemma 3 270M just made local LLMs real and it only takes about an hour to build your own. Here’s how:

OMG… you can now fine-tune your own AI model and run it entirely on your device. No servers. No API keys. No data leaks. Gemma 3 270M just made local LLMs real and it only takes about an hour to build your own. Here’s how:

Louis Gleeson

79,508 次观看 • 8 个月前