Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Cool student project from this: An AI agent that looks at code, commit messages, and context from the project management system. Then automatically writes out a detailed, human-friendly description of everything that changed and what that means for customers.

Austen Allred

481,236 subscribers

22,527 просмотров • 2 лет назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 9

Фото профиля Austen Allred

Austen Allred2 лет назад

Imagine being a software engineer who just has to write code and everything else takes care of itself automatically. Next step: automating the writing of the code.

Фото профиля Trevor Hardy

Trevor Hardy2 лет назад

Glad you found this project to be cool! Loving what I'm learning so far in your course. Shout out to @CreedJarrett / @SponsorCX for investing in me and the rest of our dev team so we can be on the cutting edge of this amazing tech! (and this project is just the beginning...) 👀

Фото профиля AfriBull

AfriBull2 лет назад

Exciting times we are in

Фото профиля Creed Mangrum

Creed Mangrum2 лет назад

That's my guy Trevor at @SponsorCX !

Фото профиля coin maver//ck

coin maver//ck2 лет назад

Student making themselves obsolete

Фото профиля Austen Allred

Austen Allred2 лет назад

You think if someone builds something that can automate write software they will be obsolete? Haha

Фото профиля Míceál

Míceál2 лет назад

Looks like a lot of similar functionality to Github Copilot Workspaces

Фото профиля Trevor Hardy

Trevor Hardy2 лет назад

@Austen Hey! I'm the student behind this project you highlighted. Loving the course so far. I have a couple of questions for you, mind if I message you?

Фото профиля David Bondo Bonderman

David Bondo Bonderman2 лет назад

Cursor already does this

Похожие видео

Meet Boxy, your new AI coding assistant 🤖 🧠 Has the full context of your project 🌱 Generates code in seconds 🔥 Refactors code from the UI 💬 Writes meaningful commit messages Read the full post or see the highlights below 👇

Meet Boxy, your new AI coding assistant 🤖 🧠 Has the full context of your project 🌱 Generates code in seconds 🔥 Refactors code from the UI 💬 Writes meaningful commit messages Read the full post or see the highlights below 👇

CodeSandbox

103,496 просмотров • 3 лет назад

Jesse on how Base supports builders "From having an idea, to starting a project, to turning that into a company, and then scaling that company to reach millions of customers" "That's what this infrastructure is set up for"

Jesse on how Base supports builders "From having an idea, to starting a project, to turning that into a company, and then scaling that company to reach millions of customers" "That's what this infrastructure is set up for"

Base

60,269 просмотров • 29 дней назад

A prototype from a BloomTech AI student: This multi-agentic system writes React components in their entirety (within the context of the company code base.) Generates fully-formed React/JavaScript + CSS + unit tests + Documentation, completely automatically.

A prototype from a BloomTech AI student: This multi-agentic system writes React components in their entirety (within the context of the company code base.) Generates fully-formed React/JavaScript + CSS + unit tests + Documentation, completely automatically.

Austen Allred

36,283 просмотров • 2 лет назад

🚀 Excited to release AIBuildAI — an AI agent that automatically builds AI models 🏆 #1 on OpenAI MLE-Bench 💻 GitHub: Building AI models still requires a lot of manual work — designing models, writing code, training them, tuning hyperparameters, and iterating on results. We developed AIBuildAI to automate much of this process. The system runs an agent loop that automatically: • analyzes the task • designs models • writes code to implement them • trains the models • tunes hyperparameters • evaluates model performance • iteratively improves the models 🏆 On OpenAI’s MLE-Bench benchmark, AIBuildAI ranked #1:

🚀 Excited to release AIBuildAI — an AI agent that automatically builds AI models 🏆 #1 on OpenAI MLE-Bench 💻 GitHub: Building AI models still requires a lot of manual work — designing models, writing code, training them, tuning hyperparameters, and iterating on results. We developed AIBuildAI to automate much of this process. The system runs an agent loop that automatically: • analyzes the task • designs models • writes code to implement them • trains the models • tunes hyperparameters • evaluates model performance • iteratively improves the models 🏆 On OpenAI’s MLE-Bench benchmark, AIBuildAI ranked #1:

Pengtao Xie

152,252 просмотров • 5 месяцев назад

Copilot now has intent detection (experimental)... It will automatically include the correct context - even if you don't specify. In this example, it detects that it needs to pass information about the entire project to answer the question and uses the workspace agent.

Copilot now has intent detection (experimental)... It will automatically include the correct context - even if you don't specify. In this example, it detects that it needs to pass information about the entire project to answer the question and uses the workspace agent.

Visual Studio Code

152,240 просмотров • 1 год назад

👷‍♂️Karmen (YC F24) is an AI assistant for construction project managers that ingests emails and texts related to projects and automatically updates construction management software, saving them up to three hours per day.

👷‍♂️Karmen (YC F24) is an AI assistant for construction project managers that ingests emails and texts related to projects and automatically updates construction management software, saving them up to three hours per day.

Y Combinator

26,902 просмотров • 1 год назад

is an AI Copilot for AWS & GCP. Configure your project from scratch, or import from GitHub to optimize existing configuration. The agent has tools to calculate cloud costs, reference docs, and fix errors automatically.

is an AI Copilot for AWS & GCP. Configure your project from scratch, or import from GitHub to optimize existing configuration. The agent has tools to calculate cloud costs, reference docs, and fix errors automatically.

Y Combinator

143,036 просмотров • 1 год назад

🚨 #ChatGPT + napari 🚨 Releasing my latest weekend project: Omega, an autonomous LLM agent that writes image processing and analysis code, fixes its mistakes, accesses the napari viewer, makes widgets, & more! OpenAI #OmegaAgent

🚨 #ChatGPT + napari 🚨 Releasing my latest weekend project: Omega, an autonomous LLM agent that writes image processing and analysis code, fixes its mistakes, accesses the napari viewer, makes widgets, & more! OpenAI #OmegaAgent

Loïc A. Royer 💻🔬⚗️

328,904 просмотров • 3 лет назад

I recreated Meta’s new AI Glasses on my Quest, and the complete source code is available! 👓 Hey everyone! I’ve received a lot of feedback and messages about my latest project, where I used the Quest to recreate the features shown during Meta’s keynote. To answer your questions I decided to create a cool video to explain how I built it but also, share the full source code on Patreon 👇 Watch the making-of: Download the source code: This project includes: ✨ A UI navigable with microgestures 🤏 A pinch & twist hand-tracking input system 🎧 An audio player with volume control via pinch & twist 📸 A camera that zooms with pinch & twist 🖼️ A carousel to browse captured pictures 🧠 And a contextual AI that reacts to what you’re looking at Hope you guys will like it and that it will help you on your own project!! 😊

I recreated Meta’s new AI Glasses on my Quest, and the complete source code is available! 👓 Hey everyone! I’ve received a lot of feedback and messages about my latest project, where I used the Quest to recreate the features shown during Meta’s keynote. To answer your questions I decided to create a cool video to explain how I built it but also, share the full source code on Patreon 👇 Watch the making-of: Download the source code: This project includes: ✨ A UI navigable with microgestures 🤏 A pinch & twist hand-tracking input system 🎧 An audio player with volume control via pinch & twist 📸 A camera that zooms with pinch & twist 🖼️ A carousel to browse captured pictures 🧠 And a contextual AI that reacts to what you’re looking at Hope you guys will like it and that it will help you on your own project!! 😊

Quentin Valembois

15,977 просмотров • 11 месяцев назад

Claude R Perrin Code SDK is under-rated One cool part with Claude Code SDK is that it supports full features out of box: - Skills - Sub agents - Hooks - ... Which means you can use claude code CLI as a debug tool to build agent, and then import to your Claude code powered agent Here is a quick example of a pptx presentation agent using Claude Code SDK + doc skills Code example from AI Builder Club by Kai:

Claude R Perrin Code SDK is under-rated One cool part with Claude Code SDK is that it supports full features out of box: - Skills - Sub agents - Hooks - ... Which means you can use claude code CLI as a debug tool to build agent, and then import to your Claude code powered agent Here is a quick example of a pptx presentation agent using Claude Code SDK + doc skills Code example from AI Builder Club by Kai:

Jason Zhou

11,981 просмотров • 10 месяцев назад

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

Milind S

12,409 просмотров • 2 месяцев назад

Today, I formally begin an open-ended endeavor that I have titled the Songs From Devotion Project. This project is a catalogue of simple choruses that have [and continue to] colored my times of personal devotion to the Lord…

Today, I formally begin an open-ended endeavor that I have titled the Songs From Devotion Project. This project is a catalogue of simple choruses that have [and continue to] colored my times of personal devotion to the Lord…

Ebele Light

35,494 просмотров • 1 месяц назад

Announcing Agent Bricks: auto-optimize agents for your domain tasks. Provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks builds out an agent system that automatically optimizes against your goals and generates domain-specific synthetic datasets, accelerating agent development without relying on manual labeling or external sources.

Announcing Agent Bricks: auto-optimize agents for your domain tasks. Provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks builds out an agent system that automatically optimizes against your goals and generates domain-specific synthetic datasets, accelerating agent development without relying on manual labeling or external sources.

Databricks

47,044 просмотров • 1 год назад

Reporter: When the budget implementation bill was going through the HOC your party voted against a clause that implements [the Alto] project and then said oops that was a mistake and voted for it, what changed between then and now? Pierre Poilievre: Nothing we're against this $90b boondoggle

Reporter: When the budget implementation bill was going through the HOC your party voted against a clause that implements [the Alto] project and then said oops that was a mistake and voted for it, what changed between then and now? Pierre Poilievre: Nothing we're against this $90b boondoggle

Scott Robertson

16,553 просмотров • 5 месяцев назад

AN OPENCLAW AI AGENT JUST DESIGNED A 3D CHARACTER IN BLENDER AND SENT IT TO A 3D PRINTER. SHE DIDN'T TOUCH A SINGLE BUTTON. This is what running an OpenClaw AI agent on a Mac Mini actually looks like. She described what she wanted. The agent did everything else. Blender opened automatically. Character designed. Put in space. Animated with blinking eyes and stomping feet. Landing page built and live. Model sliced. File sent to 3D printer. Printer started moving. All from conversation. Zero code. Zero design skills. Zero manual work. Here's why this matters beyond the demo: Custom 3D printed figures sell for $30-$200 each on Etsy and at conventions. The people making serious money aren't artists. They're the ones who can produce custom designs fast. An AI agent that goes from description to printed figure autonomously is a business model not a toy. "I was just talking to the guy and he made it happen." Bookmark this. Full demo in the video below.

AN OPENCLAW AI AGENT JUST DESIGNED A 3D CHARACTER IN BLENDER AND SENT IT TO A 3D PRINTER. SHE DIDN'T TOUCH A SINGLE BUTTON. This is what running an OpenClaw AI agent on a Mac Mini actually looks like. She described what she wanted. The agent did everything else. Blender opened automatically. Character designed. Put in space. Animated with blinking eyes and stomping feet. Landing page built and live. Model sliced. File sent to 3D printer. Printer started moving. All from conversation. Zero code. Zero design skills. Zero manual work. Here's why this matters beyond the demo: Custom 3D printed figures sell for $30-$200 each on Etsy and at conventions. The people making serious money aren't artists. They're the ones who can produce custom designs fast. An AI agent that goes from description to printed figure autonomously is a business model not a toy. "I was just talking to the guy and he made it happen." Bookmark this. Full demo in the video below.

SCOTTY BEAM

17,209 просмотров • 2 месяцев назад

🤯 100% of NVIDIA engineers code with AI—and they’re checking in 3x more code than before. At that scale, human-only code review can’t keep up. CodeRabbit review agents use models like Claude and GPT with NVIDIA Nemotron to: ✅ Pull context from code, docs, project trackers, and more ✅ Use Nemotron’s long context and reasoning to summarize ✅ …so that frontier models can flag issues and suggest fixes in minutes, not days. Join us today at 11 AM PT to see an end-to-end demo and bring your Qs: 🤗 Get Nemotron Nano 3:

🤯 100% of NVIDIA engineers code with AI—and they’re checking in 3x more code than before. At that scale, human-only code review can’t keep up. CodeRabbit review agents use models like Claude and GPT with NVIDIA Nemotron to: ✅ Pull context from code, docs, project trackers, and more ✅ Use Nemotron’s long context and reasoning to summarize ✅ …so that frontier models can flag issues and suggest fixes in minutes, not days. Join us today at 11 AM PT to see an end-to-end demo and bring your Qs: 🤗 Get Nemotron Nano 3:

NVIDIA AI Developer

100,151 просмотров • 8 месяцев назад

What if a single AI workflow could generate an entire luxury beauty campaign system from just: a model, clothes, and a cosmetic product? I built exactly that for KIKO Milano using Melius . From cinematic editorials → UGC creator ads → luxury carousel campaigns → Seedance storyboard commercials. Thread below with the full workflow breakdown, prompts, campaign system, and project link ↓

What if a single AI workflow could generate an entire luxury beauty campaign system from just: a model, clothes, and a cosmetic product? I built exactly that for KIKO Milano using Melius . From cinematic editorials → UGC creator ads → luxury carousel campaigns → Seedance storyboard commercials. Thread below with the full workflow breakdown, prompts, campaign system, and project link ↓

Zazzy

11,806 просмотров • 3 месяцев назад

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

201,127 просмотров • 1 год назад