正在加载视频...

视频加载失败

返回首页

Made myself a no code interface for optimizing prompts with DSPy. Thought I'd open source it.

hammer_mt's profile picture

Mike Taylor

8,870 subscribers

72,950 次观看 • 1 年前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

10 条评论

Mike Taylor 的头像
Mike Taylor1 年前

GitHub link:

Rogerio Chaves 的头像
Rogerio Chaves1 年前

hey hey! This is really cool, I’ve also been working on a DSPy UI, would love to hear your thoughts, let’s connect

Tommy Falkowski 的头像
Tommy Falkowski1 年前

@CShorten30 Man this looks awesome! Will definitely try this out to see what I can squeeze out of llama3.2 3B!

rohit 的头像
rohit1 年前

This is really cool. I've always found dspy somewhat difficult to grok but the interface makes it much easier. You already using it in pipelines?

Mike Taylor 的头像
Mike Taylor1 年前

I tend to take a prompt and optimize it offline, then drop the new prompt back in production. Hate using frameworks in prod, too risky and hard to understand abstractions.

Trung Le 的头像
Trung Le1 年前

I've been waiting for something like this.

Mike Taylor 的头像
Mike Taylor1 年前

Have you used DSPy before or just wanted an interface to optimise prompts?

Connor Shorten 的头像
Connor Shorten1 年前

🔥🔥🔥

diego 的头像
diego1 年前

why is this the first time I'm seeing the actual prompt generated by DSPy? (really cool btw! thanks for your effort) feels like DSPy has a really hard time getting their point across. took me a while to understand >why< I dont need to prompt myself (skill issue? sure...)

Mehrdad Yazdani 的头像
Mehrdad Yazdani1 年前

This is awesome 👏

相关视频

New short course: DSPy: Build and Optimize Agentic Apps DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with Databricks and taught by Chen Qian, co-lead of the DSPy framework. Many AI builders spend hours hand-tuning prompts. When given a set of evals, DSPy automates this process. It’s especially useful for optimizing prompts, including few-shot prompts, in complex agentic AI workflows. Further, if you switch an application to a newer LLM, performance can degrade if your prompts were optimized to the previous model. DSPy automatically optimizes the entire system for the new LLM as well, using just a few evaluation examples. This course teaches DSPy works, and best practices for using it. You’ll write programs using DSPy’s signature-based programming model, debug them with MLflow tracing -- to gain visibility into how different parts of a pipeline, as well as how the overall system, are performing -- and automatically improve their accuracy with DSPy Optimizer. Please sign up here:
3:27

New short course: DSPy: Build and Optimize Agentic Apps DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with Databricks and taught by Chen Qian, co-lead of the DSPy framework. Many AI builders spend hours hand-tuning prompts. When given a set of evals, DSPy automates this process. It’s especially useful for optimizing prompts, including few-shot prompts, in complex agentic AI workflows. Further, if you switch an application to a newer LLM, performance can degrade if your prompts were optimized to the previous model. DSPy automatically optimizes the entire system for the new LLM as well, using just a few evaluation examples. This course teaches DSPy works, and best practices for using it. You’ll write programs using DSPy’s signature-based programming model, debug them with MLflow tracing -- to gain visibility into how different parts of a pipeline, as well as how the overall system, are performing -- and automatically improve their accuracy with DSPy Optimizer. Please sign up here:

Andrew Ng

181,156 次观看 • 1 年前

This is Text-to-CAD. A new open-source prompt interface for generating CAD files through text prompts. It looks insane 🤯
0:53

This is Text-to-CAD. A new open-source prompt interface for generating CAD files through text prompts. It looks insane 🤯

Alvaro Cintas

111,304 次观看 • 1 年前

You can now build AI Agents using a no-code drag and drop interface. Fully open-source.
0:22

You can now build AI Agents using a no-code drag and drop interface. Fully open-source.

Lior Alexander

87,456 次观看 • 1 年前

"Should I start learning how to code if you haven't done it yet? I'd honestly say no. You're optimizing for the wrong skillset."
0:48

"Should I start learning how to code if you haven't done it yet? I'd honestly say no. You're optimizing for the wrong skillset."

Lenny Rachitsky

27,252 次观看 • 4 个月前

"When we saw Claude Code, we thought: one, this should probably be open source. Two, it could be built with a lot more care." OpenCode's Jay on why open source won.
0:50

"When we saw Claude Code, we thought: one, this should probably be open source. Two, it could be built with a lot more care." OpenCode's Jay on why open source won.

Toronto Tech Week

26,554 次观看 • 2 天前

i built shadow: a powerful open-source background coding agent with a real-time interface. for async, parallel work on long-running coding tasks! made in a few weeks with rajan agarwal @elijahkurien
1:00

i built shadow: a powerful open-source background coding agent with a real-time interface. for async, parallel work on long-running coding tasks! made in a few weeks with rajan agarwal @elijahkurien

ishaan dey

48,170 次观看 • 10 个月前

I'm building an open-source UI Kit with lovable This is going to have hundreds of customizable components with prompts, guides, templates and source code to accurately redesign UI with AI. 99% coded with AI. I burned through 1000+ prompts in lovable, windsurf and cursor.
0:57

I'm building an open-source UI Kit with lovable This is going to have hundreds of customizable components with prompts, guides, templates and source code to accurately redesign UI with AI. 99% coded with AI. I burned through 1000+ prompts in lovable, windsurf and cursor.

Meng To

67,089 次观看 • 1 年前

alright - verdict is in - Motion Design is solved made with HyperFrames + Claude Design btw - HyperFrames is open source, star it on github and I'll send tutorial on how i made this with 2 prompts.
0:24

alright - verdict is in - Motion Design is solved made with HyperFrames + Claude Design btw - HyperFrames is open source, star it on github and I'll send tutorial on how i made this with 2 prompts.

Bin Liu

614,641 次观看 • 1 个月前

Talk to any GitHub repository in plain English! Simply add "talkto" before "github" in a GitHub URL and instantly get a conversational interface to chat with a code base. 100% open-source!
0:24

Talk to any GitHub repository in plain English! Simply add "talkto" before "github" in a GitHub URL and instantly get a conversational interface to chat with a code base. 100% open-source!

Avi Chawla

19,845 次观看 • 1 年前

Here's the full video on using Claude Code Skills with Nano Banana Pro and ThreeJS. I've also made the both Claude skills + prompts + source code FREE (check reply) Enjoy!
24:02

Here's the full video on using Claude Code Skills with Nano Banana Pro and ThreeJS. I've also made the both Claude skills + prompts + source code FREE (check reply) Enjoy!

Chong-U

147,256 次观看 • 5 个月前

Bytedance drops an open-source Gemini Omni!!! Bernini is a new AI video generation + editing framework. > Edit videos with text prompts > Image/video references > Code available
0:31

Bytedance drops an open-source Gemini Omni!!! Bernini is a new AI video generation + editing framework. > Edit videos with text prompts > Image/video references > Code available

⚡AI Search⚡

42,745 次观看 • 10 天前

Another amazing project made with #raylib: Hawkeye A real-time 3D multi-drone flight visualizer for PX4, the open-source autopilot stack for drones and unmanned vehicles! 🤯 - Hawkeye: - Source code: by PX4 Autopilot
0:45

Another amazing project made with #raylib: Hawkeye A real-time 3D multi-drone flight visualizer for PX4, the open-source autopilot stack for drones and unmanned vehicles! 🤯 - Hawkeye: - Source code: by PX4 Autopilot

Ray

12,324 次观看 • 1 个月前

A lil' sequence that I made for Reisshub's latest vid - thought I'd leave it here 😄
0:21

A lil' sequence that I made for Reisshub's latest vid - thought I'd leave it here 😄

Rasmus "Noller" Christensen

14,551 次观看 • 1 年前

shadow is an open-source background coding agent with a real-time interface and codebase context system here's a breakdown of how it works ⬇️
0:50

shadow is an open-source background coding agent with a real-time interface and codebase context system here's a breakdown of how it works ⬇️

ishaan dey

21,582 次观看 • 10 个月前

Today I’m launching Open Interpreter, an open-source Code Interpreter that runs locally. Summarize PDFs, visualize datasets, and control your browser — all from a ChatGPT-like interface in your terminal. ● $ pip install open-interpreter $ interpreter
1:30

Today I’m launching Open Interpreter, an open-source Code Interpreter that runs locally. Summarize PDFs, visualize datasets, and control your browser — all from a ChatGPT-like interface in your terminal. ● $ pip install open-interpreter $ interpreter

killian

2,055,164 次观看 • 2 年前

Holy cow. It’s finally working.. 🤯 1) 🤖 Import design from Figma (with the help of Loader) 2) Chat with the design in Streamlit 💬 3) 🎨 Design and code is returned Will open-source the codebase tomorrow (optimizing the code today.) (Live Demo ↓)
0:23

Holy cow. It’s finally working.. 🤯 1) 🤖 Import design from Figma (with the help of Loader) 2) Chat with the design in Streamlit 💬 3) 🎨 Design and code is returned Will open-source the codebase tomorrow (optimizing the code today.) (Live Demo ↓)

peter! 🥷

233,046 次观看 • 3 年前

Introducing Qwen 3 + Deep Research! We built a deep research agent with Qwen 3 and it performed better than most open source models that we've tried. the code is completely open source and free! built with 's Langgraph Together AI and uses Perplexity Tavily for search here's the code link:
0:57

Introducing Qwen 3 + Deep Research! We built a deep research agent with Qwen 3 and it performed better than most open source models that we've tried. the code is completely open source and free! built with 's Langgraph Together AI and uses Perplexity Tavily for search here's the code link:

Soham

34,566 次观看 • 1 年前

Made an 8o spinoff for fun, thought I'd share here since I'm proud of it
0:50

Made an 8o spinoff for fun, thought I'd share here since I'm proud of it

logspa

30,687 次观看 • 8 个月前

Introducing Claude Code Templates 🚀 I originally built this to streamline how I set up new projects with Claude Code…just a small tool to make my own workflow smoother. No install, just run: npx claude-code-templates Right now, it configures Commands, Hooks, MCPs, and settings.json for JavaScript/TypeScript and Python projects. It made things so much easier for me that I decided to share it with the community. Open-source and open to ideas — feel free to contribute! Big thanks to the team at Anthropic and everyone behind Claude Code Community 🙌
0:50

Introducing Claude Code Templates 🚀 I originally built this to streamline how I set up new projects with Claude Code…just a small tool to make my own workflow smoother. No install, just run: npx claude-code-templates Right now, it configures Commands, Hooks, MCPs, and settings.json for JavaScript/TypeScript and Python projects. It made things so much easier for me that I decided to share it with the community. Open-source and open to ideas — feel free to contribute! Big thanks to the team at Anthropic and everyone behind Claude Code Community 🙌

Daniel San

28,410 次观看 • 11 个月前

I built this onboarding before Claude Code or Codex existed. I made it open source on GitHub, so take it if you want.
0:36

I built this onboarding before Claude Code or Codex existed. I made it open source on GitHub, so take it if you want.

Juanjo Valiño

56,894 次观看 • 4 个月前