Daniel Nguyen's banner

Daniel Nguyen

@daniel_nguyenx • 73,502 subscribers

Builder. Member of Technical Staff @Bolt__AI (https://t.co/uenMr6HBDG - AI workspace for power users). Expect memes 😛

Shorts

"Cursor, please fix this small bug" Cursor:

"Cursor, please fix this small bug" Cursor:

3,441,920 views

DeepSeek R1 on Groq is insanely fast. Thought for 0 seconds hahaha ⚡ * video isn't sped up

DeepSeek R1 on Groq is insanely fast. Thought for 0 seconds hahaha ⚡ * video isn't sped up

543,348 views

I recently ported BoltAI to the web platform and immediately ran into a technical challenge: How to store API keys securely? It's pretty straightforward for a native app but it's surprisingly challenging for a web app. I write a short post on my learnings below ↓

I recently ported BoltAI to the web platform and immediately ran into a technical challenge: How to store API keys securely? It's pretty straightforward for a native app but it's surprisingly challenging for a web app. I write a short post on my learnings below ↓

59,938 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

We’ve found the root cause of AWS outage today. Sorry guys.

We’ve found the root cause of AWS outage today. Sorry guys.

697,128 views • 7 months ago

Peter Thiel: “[…] if you hear the words ‘big data’ and ‘cloud computing’, you need to run away as fast as you possibly can. Just think ‘fraud’ and run away.”

Peter Thiel: “[…] if you hear the words ‘big data’ and ‘cloud computing’, you need to run away as fast as you possibly can. Just think ‘fraud’ and run away.”

1,014,631 views • 1 year ago

I bought the M4 Max 48GB RAM and first thing I did is to test local LLMs. It can barely run llama3.3 70b, but qwen2.5-coder 32b works very well. I'll test with MLX next ✌️

I bought the M4 Max 48GB RAM and first thing I did is to test local LLMs. It can barely run llama3.3 70b, but qwen2.5-coder 32b works very well. I'll test with MLX next ✌️

315,827 views • 1 year ago

Gotta love macOS 26 😆

Gotta love macOS 26 😆

102,464 views • 6 months ago

I tried the "make no mistakes" one-shot prompt joke with Gemini 3 Pro Preview and the result is actually pretty good!

I tried the "make no mistakes" one-shot prompt joke with Gemini 3 Pro Preview and the result is actually pretty good!

93,773 views • 6 months ago

I built something silly but useful ✨ Introducing: Oh One Pro Use o1-pro, o1 and o3-mini to analyze any document. ❓ Problem OpenAI's reasoning models are very powerful but it has limitations: - You need to add enough context to get the most out of it and - Model like o1-pro doesn't support document upload. You can't attach source code or PDFs 💡 Solution Oh One Pro works around this by converting your documents to xml or images. 👨‍💻 How to use it? It's incredibly simple to use. 1. Drag and drop your files into the app 2. Copy as text (xml format) or images 3. Paste into ChatGPT app Oh and it's free, no account required. Link in comment ↓

I built something silly but useful ✨ Introducing: Oh One Pro Use o1-pro, o1 and o3-mini to analyze any document. ❓ Problem OpenAI's reasoning models are very powerful but it has limitations: - You need to add enough context to get the most out of it and - Model like o1-pro doesn't support document upload. You can't attach source code or PDFs 💡 Solution Oh One Pro works around this by converting your documents to xml or images. 👨‍💻 How to use it? It's incredibly simple to use. 1. Drag and drop your files into the app 2. Copy as text (xml format) or images 3. Paste into ChatGPT app Oh and it's free, no account required. Link in comment ↓

Daniel Nguyen ⚡

171,073 views • 1 year ago

AI founders right now

AI founders right now

60,122 views • 2 years ago

No more content to load