Загрузка видео...

Не удалось загрузить видео

На главную

This is pretty amazing. Claude with computer use plus a bash tool downloads a random dataset online, installs sklearn, trains a simple classifier on the dataset, and then displays the classifier results in a webpage. All with just one prompt in under 5 minutes.

alexalbert__'s profile picture

Alex Albert

142,215 subscribers

171,988 просмотров • 1 год назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Alex Albert
Alex Albert1 год назад

This is the prompt I used: Go to find an interesting recent dataset, and download it. Install sklearn with bash tool write a .py file to split the data into train and test and make a classifier for it. (you may need to inspect the data and/or iterate if this goes poorly at first, but don't get discouraged!). Come up with some way to visualize the results of your classifier in the browser.

Фото профиля Alex Albert
Alex Albert1 год назад

This is the python file it wrote to train the classifier:

Фото профиля Alex Albert
Alex Albert1 год назад

This is the HTML code:

Фото профиля Mike Bird (Hiring)
Mike Bird (Hiring)1 год назад

Nice! Reminds me of this

Фото профиля Countdown to Opus 3.5 or 4
Countdown to Opus 3.5 or 41 год назад

Alex we need to talk

Фото профиля Eric Buess
Eric Buess1 год назад

Can it run in some kind of shadow environment with its own mouse keyboard so I can keep mine? 😂 I want to set it up on my Pi with a tunnel so I can instruct it from my iPhone or Apple Watch action button or Rabbit R1. Not sure when I’ll get time to do it but sounds fun!

Фото профиля Lorenzo Iotti
Lorenzo Iotti1 год назад

How much was this run in $?

Фото профиля Austin S. Lin
Austin S. Lin1 год назад

can you please have claude w/computer use use avante.nvim, cursor, and/or replit?

Фото профиля EDNY rape spree enjoyer
EDNY rape spree enjoyer1 год назад

I just prompted Claude to earn me $50,000 this week, it’s already up $300 today. Amazing product.

Фото профиля 🥇🥈🇩🇪🥉Darth thromBOOzyt📯
🥇🥈🇩🇪🥉Darth thromBOOzyt📯1 год назад

How many upgrades till it does actual state of the art research 👀

Похожие видео

Anthropic just announced Computer Use It allows Claude to control your computer screen based on a prompt and take actions on your behalf The use cases in agentic coding with automated debugging, customer support, and education are going to be INSANE
3:03

Anthropic just announced Computer Use It allows Claude to control your computer screen based on a prompt and take actions on your behalf The use cases in agentic coding with automated debugging, customer support, and education are going to be INSANE

Rowan Cheung

1,024,281 просмотров • 1 год назад

OpenAI just released a new model to distinguish between AI/human written text to protect against ChatGPT. The classifier was trained on a pair of AI/human written dataset. However.. I was easily able to trick it by using GPT3 to rewrite the text. Demo:
0:32

OpenAI just released a new model to distinguish between AI/human written text to protect against ChatGPT. The classifier was trained on a pair of AI/human written dataset. However.. I was easily able to trick it by using GPT3 to rewrite the text. Demo:

Lior Alexander

195,419 просмотров • 3 лет назад

I'm excited to announce the release of the Naijaweb 🇳🇬 dataset. Naijaweb is a 270,000 (230Million GPT2 tokens) document dataset of webpages which Nigerians have shown interest in, it was cleaned with the same techniques done on the Fineweb dataset by Hugging Face. A thread 🧵..
1:27

I'm excited to announce the release of the Naijaweb 🇳🇬 dataset. Naijaweb is a 270,000 (230Million GPT2 tokens) document dataset of webpages which Nigerians have shown interest in, it was cleaned with the same techniques done on the Fineweb dataset by Hugging Face. A thread 🧵..

Saheedniyi

188,158 просмотров • 1 год назад

Regime classifier. What is a regime? Who is a regime? This satire is part of the episode we did with Seyed Mohammad Marandi on NOOW Tehran Tadhg
4:22

Regime classifier. What is a regime? Who is a regime? This satire is part of the episode we did with Seyed Mohammad Marandi on NOOW Tehran Tadhg

Nicole Jenes

25,005 просмотров • 2 месяцев назад

I use Perplexity Computer for any meetings in my daily work. Simply giving it a prompt, it provides me with all the necessary information. It is a very useful tool. See how I complete all my meetings just by giving prompts.
0:31

I use Perplexity Computer for any meetings in my daily work. Simply giving it a prompt, it provides me with all the necessary information. It is a very useful tool. See how I complete all my meetings just by giving prompts.

Md Naimul Kadir

29,218 просмотров • 2 месяцев назад

Most "agentic" failures happen because the model lacks specific domain knowledge. Here I'm showing how loading a Skills Plugin solves that for dataset generation. I turned a research paper (shows fine-tuning dataset creation from books) into a Skill and just gave a book link and asked it to generate the dataset. Claude Code produced a clean SFT-ready dataset from a single URL. The same process can be applied to anything.
0:58

Most "agentic" failures happen because the model lacks specific domain knowledge. Here I'm showing how loading a Skills Plugin solves that for dataset generation. I turned a research paper (shows fine-tuning dataset creation from books) into a Skill and just gave a book link and asked it to generate the dataset. Claude Code produced a clean SFT-ready dataset from a single URL. The same process can be applied to anything.

Muratcan Koylan

104,519 просмотров • 5 месяцев назад

last year we wasted $120K and 6 months on a fancy landing page this year I vibe coded a better one in a weekend starting with a very simple claude code prompt:
0:33

last year we wasted $120K and 6 months on a fancy landing page this year I vibe coded a better one in a weekend starting with a very simple claude code prompt:

brett goldstein

58,255 просмотров • 3 месяцев назад

⚡With our beginner-friendly interface, you can create a job on EarnFi in just 5 simple steps. This job was created in under a minute and reached 80% completion within 10 minutes. Simple. Fast. Efficient. Watch the tutorial below, then head over to to create your job.
0:56

⚡With our beginner-friendly interface, you can create a job on EarnFi in just 5 simple steps. This job was created in under a minute and reached 80% completion within 10 minutes. Simple. Fast. Efficient. Watch the tutorial below, then head over to to create your job.

EarnFi

14,612 просмотров • 5 месяцев назад

.tobi lutke has been running a keylogger and auto-screenshotting his computer every 10 minutes for the last 15 years. That's a crazy person move, and a wild dataset to have on yourself.
2:03

.tobi lutke has been running a keylogger and auto-screenshotting his computer every 10 minutes for the last 15 years. That's a crazy person move, and a wild dataset to have on yourself.

Acquired Podcast

113,496 просмотров • 9 месяцев назад

Claude Code: Auto mode Auto mode lets Claude safely complete long-running tasks without asking permission for every action. But how does it work? 4 key terms: • Classifier: a separate model that approves or denies each action based on your intent and scope • Filtering: the classifier only sees your messages and Claude's tool calls, not Claude’s reasoning or tool outputs, so it isn't influenced when making decisions • Tier check: read-only and easily-undone actions (like edits inside your repo) skip the classifier; everything else goes through it • Probe: a server-side check that scans incoming content, like web pages, for prompt injection and flags it to Claude I'm working on a longer video that explains how auto mode works and how to configure it. What questions do you have about it?
0:52

Claude Code: Auto mode Auto mode lets Claude safely complete long-running tasks without asking permission for every action. But how does it work? 4 key terms: • Classifier: a separate model that approves or denies each action based on your intent and scope • Filtering: the classifier only sees your messages and Claude's tool calls, not Claude’s reasoning or tool outputs, so it isn't influenced when making decisions • Tier check: read-only and easily-undone actions (like edits inside your repo) skip the classifier; everything else goes through it • Probe: a server-side check that scans incoming content, like web pages, for prompt injection and flags it to Claude I'm working on a longer video that explains how auto mode works and how to configure it. What questions do you have about it?

Delba

40,417 просмотров • 8 дней назад

Introducing the Parallel FindAll API. Create an entire dataset with a single search query. For example: "Find all dental practices in Ohio with a 4+ star review on Google"
0:39

Introducing the Parallel FindAll API. Create an entire dataset with a single search query. For example: "Find all dental practices in Ohio with a 4+ star review on Google"

Parallel Web Systems

277,628 просмотров • 7 месяцев назад

The internet is the greatest dataset ever created. Today, we're launching the Riveter Dataset Builder to make it possible for anyone to get custom, fresh data from a prompt.
0:33

The internet is the greatest dataset ever created. Today, we're launching the Riveter Dataset Builder to make it possible for anyone to get custom, fresh data from a prompt.

Abby Grills

24,611 просмотров • 2 месяцев назад

Released by Reality Labs at Meta Research at #ECCV2024, Nymeria is a large-scale multimodal egocentric dataset for full-body motion understanding with potential applications in VR/MR headsets, smart glasses and more. More on this work + access to the dataset ➡️
0:25

Released by Reality Labs at Meta Research at #ECCV2024, Nymeria is a large-scale multimodal egocentric dataset for full-body motion understanding with potential applications in VR/MR headsets, smart glasses and more. More on this work + access to the dataset ➡️

AI at Meta

52,312 просмотров • 1 год назад

The amazing tool removes all the grass in a few minutes
0:21

The amazing tool removes all the grass in a few minutes

Economics and Agriculture

90,386 просмотров • 1 месяц назад

Very excited to release the Open X-Embodiment Dataset today — the largest robot dataset to date with 1M+ trajectories! Robotics needs more data & this is a big step! There’s lots to unpack here, so let’s do a deep dive into the dataset! 🧵1/15
0:36

Very excited to release the Open X-Embodiment Dataset today — the largest robot dataset to date with 1M+ trajectories! Robotics needs more data & this is a big step! There’s lots to unpack here, so let’s do a deep dive into the dataset! 🧵1/15

Karl Pertsch

111,054 просмотров • 2 лет назад

Introducing... The Base Skills Repo 📙🔧 Power your Claude, Codex, OpenClaw with skills to build on Base I show in this video how I one shot a Base Pay demo in one simple prompt with the Base Account skill Use it now: npx skills add base/skills
3:30

Introducing... The Base Skills Repo 📙🔧 Power your Claude, Codex, OpenClaw with skills to build on Base I show in this video how I one shot a Base Pay demo in one simple prompt with the Base Account skill Use it now: npx skills add base/skills

Youssef

56,202 просмотров • 3 месяцев назад

Hey everyone, I just want to say that i'm really really sorry and wanted to make a public apology. I did let the tools that I use every day (because they're objectively the best at everything) bias my content. Lets give a try. I now realize the tool in the video below is the best design tool. And there's starting templates in a simple interface. And I can deploy to Vercel in one prompt. And a video is coming out later today on how i build this in 45 minutes using Cursor.
2:48

Hey everyone, I just want to say that i'm really really sorry and wanted to make a public apology. I did let the tools that I use every day (because they're objectively the best at everything) bias my content. Lets give a try. I now realize the tool in the video below is the best design tool. And there's starting templates in a simple interface. And I can deploy to Vercel in one prompt. And a video is coming out later today on how i build this in 45 minutes using Cursor.

Riley Brown

115,837 просмотров • 1 год назад

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base
1:47

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Malte Ubl

124,713 просмотров • 5 месяцев назад

train YOLOv9 on your dataset tutorial - run inference with a pre-trained COCO model - fine-tune model on custom dataset - evaluate the trained model - run inference with a fine-tuned model blogpost: ↓ read more
0:30

train YOLOv9 on your dataset tutorial - run inference with a pre-trained COCO model - fine-tune model on custom dataset - evaluate the trained model - run inference with a fine-tuned model blogpost: ↓ read more

SkalskiP

111,792 просмотров • 2 лет назад

« Hey Gadget, build me a CRM. » A single prompt in one end. A fully hosted, well designed internal tool out the other end, in under 4 minutes. Full code accessible and editable with further prompting (or by hand). Beta opens in weeks. Waitlist at
1:49

« Hey Gadget, build me a CRM. » A single prompt in one end. A fully hosted, well designed internal tool out the other end, in under 4 minutes. Full code accessible and editable with further prompting (or by hand). Beta opens in weeks. Waitlist at

Mohammad

27,392 просмотров • 1 год назад