Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

MattGPT, answering the important questions. - 100% TypeScript - AI SDK - Question-matching retrieval based on a custom dataset - Clack for beautiful CLI

mattpocockuk's profile picture

Matt Pocock

354,350 subscribers

40,703 Aufrufe • vor 1 Jahr •via X (Twitter)

BildungKunstWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Matt Pocock
Matt Pocockvor 1 Jahr

Once nice thing about using RAG (instead of finetuning or pretraining) is that it's super cheap to add or modify behaviour. For instance, I've added a section on hover behaviour:

Profilbild von Matt Pocock
Matt Pocockvor 1 Jahr

TS Performance

Profilbild von Christian Esmann
Christian Esmannvor 2 Jahren

I just launched an all-in-one template for cross-platform development, based on the stack I use myself everyday. Expo, NextJS, TypeScript, Tailwind, Firebase, AppsFlyer, Authentication, Analytics, In-App Purchases, Stripe and a lot more, setup by default.

Profilbild von Pavel Svitek 🇨🇭
Pavel Svitek 🇨🇭vor 1 Jahr

Is this the future of personal websites? I thought about this recently.

Profilbild von Matt Pocock
Matt Pocockvor 1 Jahr

It's still relatively tricky to pull off. And I don't really like the idea of red teaming your own personal site to make sure you don't say anything stupid.

Profilbild von AI Carlos
AI Carlosvor 1 Jahr

Love the tech stack behind MattGPT!

Profilbild von Simplr
Simplrvor 1 Jahr

Matt Proof-Of-Concept-ock

Profilbild von trav
travvor 1 Jahr

mattgpt amazing name lol

Profilbild von Mehmet Emin
Mehmet Eminvor 1 Jahr

Is it answering only typescript questions?

Profilbild von Matt Pocock
Matt Pocockvor 1 Jahr

Yep

Profilbild von SELF⌁DESTRUCTION.js
SELF⌁DESTRUCTION.jsvor 1 Jahr

Youve outdone yourself 👏🏼👏🏼👏🏼

Ähnliche Videos

🔥 We fine-tuned Gemma 3 using Unsloth AI on a custom instruction dataset scraped and built with . The model is now able to answer questions about OpenAI Agents SDK documentation. Check out the demo below👇
0:48

🔥 We fine-tuned Gemma 3 using Unsloth AI on a custom instruction dataset scraped and built with . The model is now able to answer questions about OpenAI Agents SDK documentation. Check out the demo below👇

Eric Ciarla (hiring)

28,794 Aufrufe • vor 1 Jahr

Today we're open sourcing a technical preview of the GitHub Copilot CLI SDK. Build agents with custom tools in Go, Python, TypeScript, and C#. Built on the same agent loop that powers the Copilot CLI and GitHub Coding Agent. Supports BYOK, and any model. Here is the Copilot CLI driving Excel:
0:29

Today we're open sourcing a technical preview of the GitHub Copilot CLI SDK. Build agents with custom tools in Go, Python, TypeScript, and C#. Built on the same agent loop that powers the Copilot CLI and GitHub Coding Agent. Supports BYOK, and any model. Here is the Copilot CLI driving Excel:

Evan Boyle

184,599 Aufrufe • vor 9 Monaten

Frens don't let frens put private keys on their Claw You can now use the WalletConnect CLI SDK (beta) to access real funds in your CLI. The SDK comes with a sample CLI for the WCT staking app "I want to stake 1000 WCT for 2 weeks"
1:40

Frens don't let frens put private keys on their Claw You can now use the WalletConnect CLI SDK (beta) to access real funds in your CLI. The SDK comes with a sample CLI for the WCT staking app "I want to stake 1000 WCT for 2 weeks"

𝒟𝑒𝓇𝑒𝓀 ✨

11,173 Aufrufe • vor 7 Monaten

New in Neon this week: - The Electric team joins us - An `inspect_database` tool for agents - A Herdr panel - Tons of Vercel updates: Neon skills in the Vercel CLI, AI gateway in AI SDK, Agent Plugins package - More additions to the Neon CLI
1:20

New in Neon this week: - The Electric team joins us - An `inspect_database` tool for agents - A Herdr panel - Tons of Vercel updates: Neon skills in the Vercel CLI, AI gateway in AI SDK, Agent Plugins package - More additions to the Neon CLI

Neon

10,650 Aufrufe • vor 2 Monaten

Introducing the best ML research assistant on the Internet Ask questions like “Should I use RLVR or Rubrics when training a model for agentic document retrieval?” and get evidence-based answers Voyage through the latest AI research and ideate experiments with our assistant
0:43

Introducing the best ML research assistant on the Internet Ask questions like “Should I use RLVR or Rubrics when training a model for agentic document retrieval?” and get evidence-based answers Voyage through the latest AI research and ideate experiments with our assistant

alphaXiv

22,245 Aufrufe • vor 7 Monaten

I packaged up a little Effect | TypeScript for the AI Era-based HTTP cassette recorder library we made for testing slow, expensive, & flaky LLM calls in OpenCode. Here's a demo.
2:41

I packaged up a little Effect | TypeScript for the AI Era-based HTTP cassette recorder library we made for testing slow, expensive, & flaky LLM calls in OpenCode. Here's a demo.

Kit Langton

28,780 Aufrufe • vor 3 Monaten

Sébastien Bubeck on the OpenAI Podcast: People think AI is only good at answering questions. OpenAI's internal agents are now asking questions so good that researchers are writing papers based on them. They're also finding and correcting mistakes in published work. His timeline for models doing everything human researchers do? 1-2 years.
0:54

Sébastien Bubeck on the OpenAI Podcast: People think AI is only good at answering questions. OpenAI's internal agents are now asking questions so good that researchers are writing papers based on them. They're also finding and correcting mistakes in published work. His timeline for models doing everything human researchers do? 1-2 years.

Chubby♨️

20,094 Aufrufe • vor 5 Monaten

Streaming Smart Glasses Camera to a Quest 3 in WebXR A-Frame Using our Wearables SDK, we’re able to stream camera data from the Omi AI Omi Glass (based on the Seeed Studio XIAO ESP32-S3 Sense running custom firmware) to the Quest 3 over WebSockets in the Oculus Browser
0:45

Streaming Smart Glasses Camera to a Quest 3 in WebXR A-Frame Using our Wearables SDK, we’re able to stream camera data from the Omi AI Omi Glass (based on the Seeed Studio XIAO ESP32-S3 Sense running custom firmware) to the Quest 3 over WebSockets in the Oculus Browser

Brilliant Wear

18,572 Aufrufe • vor 9 Monaten

'Surely, this is a time now for Sir Keir Starmer to start answering questions with proper answers.' Reform UK MP Lee Anderson slams the PM for not engaging with his question on protecting young women and girls at today's PMQs.
1:38

'Surely, this is a time now for Sir Keir Starmer to start answering questions with proper answers.' Reform UK MP Lee Anderson slams the PM for not engaging with his question on protecting young women and girls at today's PMQs.

GB News

57,070 Aufrufe • vor 3 Monaten

Just open sourced a template for using the new Grok Voice Agents in Expo ⬦ Dynamic Rive animations from Vercel AI Elements ⬦ AI SDK v7 and Tailwind ⬦ Custom Grok voices and personalities Source below ↓
0:34

Just open sourced a template for using the new Grok Voice Agents in Expo ⬦ Dynamic Rive animations from Vercel AI Elements ⬦ AI SDK v7 and Tailwind ⬦ Custom Grok voices and personalities Source below ↓

Evan Bacon 🥓

64,520 Aufrufe • vor 3 Monaten

Our OSS engineer Clelia Bertelli (🦀/acc) recently built 𝗹𝗶𝘁𝗲𝘀𝗲𝗮𝗿𝗰𝗵, a fully local document ingestion and retrieval CLI/TUI application powered by LiteParse ⚡ litesearch demonstrates how developers can assemble a high-performance, local-first retrieval pipeline using open tools from across the ecosystem: • Parsing: LiteParse, the fast and accurate document parser we recently open sourced • Chunking: @ChonkieAI • Embeddings: A local Nomic model via Hugging Face transformers.js • Vector storage: A local Qdrant edge shard (custom-built in Rust and compiled as a native add-on) • Retrieval: Query stored files with optional path-based filtering and configurable relevance thresholds • Runtime: Bun for speed and versatility 💻 Check out the repository and try it yourself: 📚 LiteParse docs:
0:32

Our OSS engineer Clelia Bertelli (🦀/acc) recently built 𝗹𝗶𝘁𝗲𝘀𝗲𝗮𝗿𝗰𝗵, a fully local document ingestion and retrieval CLI/TUI application powered by LiteParse ⚡ litesearch demonstrates how developers can assemble a high-performance, local-first retrieval pipeline using open tools from across the ecosystem: • Parsing: LiteParse, the fast and accurate document parser we recently open sourced • Chunking: @ChonkieAI • Embeddings: A local Nomic model via Hugging Face transformers.js • Vector storage: A local Qdrant edge shard (custom-built in Rust and compiled as a native add-on) • Retrieval: Query stored files with optional path-based filtering and configurable relevance thresholds • Runtime: Bun for speed and versatility 💻 Check out the repository and try it yourself: 📚 LiteParse docs:

LlamaIndex 🦙

14,900 Aufrufe • vor 6 Monaten

3D hand tracking on smart glasses Not only can we stream camera data with our Wearables SDK, but we can run MediaPipe for hand tracking, applying it in WebXR environments like Three.js and A-Frame Works with compatible smart glasses, in this case the Omi AI Omi Glass, based on the Seeed Studio XIAO ESP32-S3 Sense (running our custom Firmware)
0:30

3D hand tracking on smart glasses Not only can we stream camera data with our Wearables SDK, but we can run MediaPipe for hand tracking, applying it in WebXR environments like Three.js and A-Frame Works with compatible smart glasses, in this case the Omi AI Omi Glass, based on the Seeed Studio XIAO ESP32-S3 Sense (running our custom Firmware)

Brilliant Wear

79,540 Aufrufe • vor 9 Monaten

Want to ask AI Scott Adams a question about anything? You can generate your own custom AI Scott Video on ANY topic in minutes for free.
0:20

Want to ask AI Scott Adams a question about anything? You can generate your own custom AI Scott Video on ANY topic in minutes for free.

AI Coffee with AI Scott Adams

158,294 Aufrufe • vor 5 Monaten

Check it out: An entire lesson from BloomTech's AI for Developer Productivity course! Fundamentals of RAG (Retrieval-Augmented-Generation). How we enhance accuracy and reliability of generative AI models. This is the foundation we build on to give AI important context.
1:00:27

Check it out: An entire lesson from BloomTech's AI for Developer Productivity course! Fundamentals of RAG (Retrieval-Augmented-Generation). How we enhance accuracy and reliability of generative AI models. This is the foundation we build on to give AI important context.

Austen Allred

79,529 Aufrufe • vor 2 Jahren

Looking to use #AI to help you learn #medicine? From AI-powered search to custom board exam questions on any topic, we have a custom feature available for you! Check it out FREE at 🧠
1:12

Looking to use #AI to help you learn #medicine? From AI-powered search to custom board exam questions on any topic, we have a custom feature available for you! Check it out FREE at 🧠

Neural Consult

3,749,890 Aufrufe • vor 2 Jahren

Advice for AI engineers 💡 A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... and costs 50 times less. For example, LFM2.5-VL-1.6B by Liquid AI running locally at full speed with llama.cpp ↓
0:24

Advice for AI engineers 💡 A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5... ... and costs 50 times less. For example, LFM2.5-VL-1.6B by Liquid AI running locally at full speed with llama.cpp ↓

Pau Labarta Bajo

80,352 Aufrufe • vor 8 Monaten

Trump: I watched AOC answering questions in Munich. This was not a good look for the United States. I watched Gavin Newscum answering questions in Munich and this was a bad look for our country. These two people are incompetent and at least Hillary's competent. She's just Trump deranged. She was so deranged. She is an angry woman. But I watched the other two speaking and answering basic questions. Look, Gavin has destroyed California and AOC — I never really got her to — I never heard her speak very much. And they started answering questions. She had no idea what was happening. She had no idea how to answer, you know, very important questions concerning the world.
0:54

Trump: I watched AOC answering questions in Munich. This was not a good look for the United States. I watched Gavin Newscum answering questions in Munich and this was a bad look for our country. These two people are incompetent and at least Hillary's competent. She's just Trump deranged. She was so deranged. She is an angry woman. But I watched the other two speaking and answering basic questions. Look, Gavin has destroyed California and AOC — I never really got her to — I never heard her speak very much. And they started answering questions. She had no idea what was happening. She had no idea how to answer, you know, very important questions concerning the world.

Clash Report

88,300 Aufrufe • vor 7 Monaten

IMPORTANT live TONIGHT Sunday 6pm! I'll be opening my "brown envelope" live & answering 5 crucial questions in this video 👇 To get the most out of it print: Want to ask a question in chat will need to be subscribed Pls shr/RT
1:44

IMPORTANT live TONIGHT Sunday 6pm! I'll be opening my "brown envelope" live & answering 5 crucial questions in this video 👇 To get the most out of it print: Want to ask a question in chat will need to be subscribed Pls shr/RT

Dr Tony Goldstone

39,012 Aufrufe • vor 2 Jahren