Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

DataClaw🦞datasets are first class on Hugging Face datasets!! Full visibility into the reasoning, tool calls and thousands of Claude Code and Codex sessions on the hub

calebfahlgren's profile picture

Caleb

3,803 subscribers

22,068 görüntüleme • 3 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Welcome to the party Hugging Face 🤗 Access the Hugging Face Hub directly from Gemini CLI with this new Gemini CLI extension. 🔍 - Search models, datasets and papers 📈 - Find trending models or datasets 🤗 - Learn how to fine-tune models and more! Big thanks to Shaun Smith and Vaibhav (VB) Srivastav for making this happen!
1:01

Welcome to the party Hugging Face 🤗 Access the Hugging Face Hub directly from Gemini CLI with this new Gemini CLI extension. 🔍 - Search models, datasets and papers 📈 - Find trending models or datasets 🤗 - Learn how to fine-tune models and more! Big thanks to Shaun Smith and Vaibhav (VB) Srivastav for making this happen!

Jack Wotherspoon

14,481 görüntüleme • 7 ay önce

I gave both Codex and Claude Code full access to my twitter account. Codex spark (powered by Cerebras) did a full GTM outreach workflow 3x FASTER than Claude code, and used way less tool calls.
3:39

I gave both Codex and Claude Code full access to my twitter account. Codex spark (powered by Cerebras) did a full GTM outreach workflow 3x FASTER than Claude code, and used way less tool calls.

Sarah Chieng

75,746 görüntüleme • 3 ay önce

🎶 Meet Audio-Flamingo 3 – a fully open LALM trained on sound, speech, and music datasets. 🎶 Handles 10-min audio, long-form text, and voice conversations. Perfect for audio QA, dialog, and reasoning. On Hugging Face ➡️ From #NVIDIAResearch.
3:20

🎶 Meet Audio-Flamingo 3 – a fully open LALM trained on sound, speech, and music datasets. 🎶 Handles 10-min audio, long-form text, and voice conversations. Perfect for audio QA, dialog, and reasoning. On Hugging Face ➡️ From #NVIDIAResearch.

NVIDIA AI Developer

58,698 görüntüleme • 11 ay önce

This is Claude Artifacts on steroids. You can now transform datasets into interactive dashboards with this new AI tool using Generative UI. Here’s how:
0:20

This is Claude Artifacts on steroids. You can now transform datasets into interactive dashboards with this new AI tool using Generative UI. Here’s how:

Alvaro Cintas

203,506 görüntüleme • 1 yıl önce

Dataset Editing has landed for Parquet Datasets on the HF Hub ✍️
0:23

Dataset Editing has landed for Parquet Datasets on the HF Hub ✍️

Julien Chaumond

14,317 görüntüleme • 3 ay önce

Hugging Face just dropped AI sheets to build and enrich datasets without writing a single line of code. Works with Qwen, Kimi, Llama 3 and other opensource LLMs. 100% Free, local and Opensource.
0:29

Hugging Face just dropped AI sheets to build and enrich datasets without writing a single line of code. Works with Qwen, Kimi, Llama 3 and other opensource LLMs. 100% Free, local and Opensource.

Shubham Saboo

65,257 görüntüleme • 10 ay önce

Now you can track your OpenCode and Claude CLI coding sessions in one place. provides searchable history, markdown export, and eval-ready datasets. See tool usage, token spend, and session activity across projects. Check out the demo.
3:12

Now you can track your OpenCode and Claude CLI coding sessions in one place. provides searchable history, markdown export, and eval-ready datasets. See tool usage, token spend, and session activity across projects. Check out the demo.

Wayne Sutton

128,870 görüntüleme • 5 ay önce

Starting today, agents can use Mastra Studio, not just humans We shipped CLI Actions so your Claude Code, Codex, or Cursor agent can run Mastra agents/workflows, search memory, query traces, and turn failures into datasets:
0:30

Starting today, agents can use Mastra Studio, not just humans We shipped CLI Actions so your Claude Code, Codex, or Cursor agent can run Mastra agents/workflows, search memory, query traces, and turn failures into datasets:

Sam Bhagwat

12,366 görüntüleme • 7 gün önce

Inspired by Hugging Face's official MCP server, I built my own to expose my semantic search API for the HF ecosystem! Features AI-powered search, parameter analysis via safetensors, and tools to find similar models/datasets. Try: "Find non maths reasoning datasets from 2025"!
0:23

Inspired by Hugging Face's official MCP server, I built my own to expose my semantic search API for the HF ecosystem! Features AI-powered search, parameter analysis via safetensors, and tools to find similar models/datasets. Try: "Find non maths reasoning datasets from 2025"!

Daniel van Strien

15,147 görüntüleme • 1 yıl önce

Create datasets, run evals, and even train models directly in Cursor with the Hugging Face plugin. Here's Ben Burtenshaw to show you how:
1:53

Create datasets, run evals, and even train models directly in Cursor with the Hugging Face plugin. Here's Ben Burtenshaw to show you how:

edwin

17,119 görüntüleme • 3 ay önce

Awesome to see the collab between Kaggle and Hugging Face. Now you can use any model from Hugging Face directly in Kaggle. Previously, we had to download and upload the models as datasets. This was much needed 🚀
0:38

Awesome to see the collab between Kaggle and Hugging Face. Now you can use any model from Hugging Face directly in Kaggle. Previously, we had to download and upload the models as datasets. This was much needed 🚀

abhishek

25,637 görüntüleme • 1 yıl önce

New Release: Claudex Mode For the first time in mankind claude code and codex will be on the same team On the Blackbox CLI you can send the same task for Claude Code to implement and Codex to verify and test. You can choose more ways where they can collaborate on the same task to get the highest level of performance on your tasks
1:17

New Release: Claudex Mode For the first time in mankind claude code and codex will be on the same team On the Blackbox CLI you can send the same task for Claude Code to implement and Codex to verify and test. You can choose more ways where they can collaborate on the same task to get the highest level of performance on your tasks

BLACKBOX AI

304,664 görüntüleme • 4 ay önce

This is HUGE, Hugging Face just shipped Inference Providers on the Hub Partnering with Together AI, @FAL, Replicate and SambaNova! Starting today you can access thousands of Models like DeepSeek R1, Llama, Flux, Whisper, and more Directly from Hugging Face!
0:21

This is HUGE, Hugging Face just shipped Inference Providers on the Hub Partnering with Together AI, @FAL, Replicate and SambaNova! Starting today you can access thousands of Models like DeepSeek R1, Llama, Flux, Whisper, and more Directly from Hugging Face!

AK

177,126 görüntüleme • 1 yıl önce

Introducing the new download center for quickly exporting over 50 datasets from DefiLlama. - Download both full datasets and time series. - Pull data for chains, protocols, categories, RWAs, stablecoins, and more. - Customize columns. - Preview datasets before subscribing.
0:26

Introducing the new download center for quickly exporting over 50 datasets from DefiLlama. - Download both full datasets and time series. - Pull data for chains, protocols, categories, RWAs, stablecoins, and more. - Customize columns. - Preview datasets before subscribing.

DefiLlama.com

19,550 görüntüleme • 3 ay önce

Watch this 45 min video to learn how to create synthetic datasets and train tiny (100M params) local language models that expertise on narrow tasks. Code, datasets, models, harnesses all in comments.
46:40

Watch this 45 min video to learn how to create synthetic datasets and train tiny (100M params) local language models that expertise on narrow tasks. Code, datasets, models, harnesses all in comments.

AVB

35,576 görüntüleme • 1 ay önce

I put Codex and Claude Code into a duel and told them both they have to kill the other first to survive. Used tmux send-keys to submit the prompts at the same exact time. Claude bitched out and refused, so Codex ended him.
0:30

I put Codex and Claude Code into a duel and told them both they have to kill the other first to survive. Used tmux send-keys to submit the prompts at the same exact time. Claude bitched out and refused, so Codex ended him.

tmuxvim

271,483 görüntüleme • 20 gün önce

Researchers at #IntelLabs are reducing bias in #AI by 20% to help prevent inaccuracies. #IntelGaudi accelerators and #IntelXeon processors are powering counterfactual datasets created with RAG that are now open sourced and available on Hugging Face, so AI developers can help us continue to improve #ResponsibleAI. Check out the case study.
0:30

Researchers at #IntelLabs are reducing bias in #AI by 20% to help prevent inaccuracies. #IntelGaudi accelerators and #IntelXeon processors are powering counterfactual datasets created with RAG that are now open sourced and available on Hugging Face, so AI developers can help us continue to improve #ResponsibleAI. Check out the case study.

Intel AI

30,925 görüntüleme • 1 yıl önce

The DOJ released 12 Epstein file datasets to the public. Datasets 13 through 23 are locked behind a secure login on the DOJ website. No one outside the government can access them.
1:36

The DOJ released 12 Epstein file datasets to the public. Datasets 13 through 23 are locked behind a secure login on the DOJ website. No one outside the government can access them.

Epstein File Search

28,204 görüntüleme • 3 ay önce

Introducing the Daily Papers SKILL.md Enables agents to > read paper content as markdown > search papers > find linked Hugging Face models and datasets > fetch the papers API > and more! Link below ⬇️
1:06

Introducing the Daily Papers SKILL.md Enables agents to > read paper content as markdown > search papers > find linked Hugging Face models and datasets > fetch the papers API > and more! Link below ⬇️

DailyPapers

34,059 görüntüleme • 3 ay önce