Browse All Videos
Discover videos from the community
Big Brain AI - Eric Schmidt's advice for making money in AI right now: "Found an ag...
Eric Schmidt's advice for making money in AI right now: "Found an agentic AI company. Not one desig
View Details
Naval - Vibe Coding Is the New Product Management “There’s been a shift—a ma...
Vibe Coding Is the New Product Management “There’s been a shift—a marked pronouncement in the last
View Details
GREG ISENBERG - how to use obsidian + claude code to build a 24/7 personal operating ...
how to use obsidian + claude code to build a 24/7 personal operating system and build your startup:
View Details
Most people think AI = ChatGPT. But for high-security industries like Finance or Healthcare, sending data to a Cloud API is a huge “No.” To solve this, you need to shift from Cloud LLMs to Local LLMs. Here is how you Decode the “No Internet” problem: 1️⃣ Pick an Open-Source Model: Instead of OpenAI, use models like Llama 3 (Meta), Mistral, or Gemma (Google). These are weights you can actually download and own. 2️⃣ Quantization is Key: A massive model won’t fit on standard office servers. Use Quantization (4-bit or 8-bit) to compress the model so it runs fast on local hardware without losing much “intelligence.” 3️⃣ Local Serving Tools: Use frameworks like Ollama, vLLM, or LocalAI. These tools create a local API that works exactly like ChatGPT but stays 100% inside the company’s firewall. 4️⃣ Offline Vector Database: For the RAG pipeline, use local databases like ChromaDB or FAISS. This ensures that even the “search” part of your AI never hits the public web. Privacy isn’t a feature; it’s a requirement. 🛠️ Follow Lets Decode AI to learn how to build AI that works anywhere, even in a bunker. #AI #Privacy #DataSecurity #LocalLLM #Llama3 Ollama SoftwareEngineering GenerativeAI LetsDecodeAI TechCareer
🎵 Outro music 🎵
View Details
Cam Young’s Perfect Downswing Sequence Explained 🏌️♂️
Cam Young’s Perfect Downswing Sequence Explained 🏌️♂️ Cam Young has been impressive at this year’s
View Details
755K views · 28K reactions | Our #3 fan favorite of 2025 🥰 #blacklab #labrador #labradorretriever #lab #fblifestyle | Remi and Walter
Our #3 fan favorite of 2025 🥰 #blacklab #labrador #labradorretriever #lab #fblifestyle
View Details
Where are all of my helicopter parents at Quit clearing the path for the kid Prep the kid for the path helicoptermom momoftiktok helicopterparents motherhood
Thanks for watching!
View Details
This drill is so easy ✅ If you want a neutral swing rather than a path that is too in-to-out or out-to-in do this!!!! It can help even out your big slices and hooks Comment SWING PATH & I will send you more information on why ⛳️ @travismathew_eu @travismathewwomens_eu #golf #golfdrill #golfswing #golftip
If you want it, take it I should've said it before Try to hide it, fake it I can't pretend...
View Details
Comment “DRILL” to unlock my new custom $39 swing evaluation and get custom exercises built around your movement faults. (2-3) Your spine angle in transition decides how pure you strike it.
It's farming, it's farming And she got it done, like the way she farms And she gon' perform it,...
View Details
92% of golfers early extend, fix it by getting punched!
Stop doing this, feeling like you're getting punched towards the ball, and instead, feel like...
View Details
Shallowing the club has never been this easy before ⛳️⬇️
Think dropping your hands down the wall, not throwing them out towards the golf ball
View Details
If you practice like in the video, you’ll feel pressure in your left foot and a pushing force through your right leg.🏌🏻♀️ Of course, if you sway, you won’t feel much at all.🙅♀️
왼팔은 여기를 돌리고, 왼팔은 여기를 돌려주면 됩니다
View Details
This Is Why You Can’t Square the Clubface at Impact ❌ If you’re struggling to square the clubface at impact, the problem might start way earlier than you think, in your takeaway. Many golfers over-hinge their wrists, throwing off their club path, face position, and timing. In this video, I’ll show you what a proper takeaway looks like for more consistent, powerful contact 💪
No transcript available
View Details
Every great ball-striker shallows exactly like this ⛳️⬇️ Unlock the move every great ball-striker uses. When you load the club vertical and then let it shallow, the shaft drops into the slot, your rotation opens up, and the swing finally feels effortless instead of forced. This is the transition that fixes early casting, over-the-top moves, and stuck trails arms—all in one simple feel. Slow it down, rehearse the pattern, and watch your contact, path, and compression change instantly ⛳️⬇️ Comment the word shallow for a 5 minute break down in how to properly shallow the club ⛳️ #golf #golfinstruction #golfdrills #golftips
Every great ball strike is shallow exactly like this
View Details
Everyone thinks LLM leaks are “model problems.” Actually: they’re architecture problems. Here’s the framework I use in production Access, Context, Output. ⚡ The Over-Entitled Retriever Insight: Most leaks happen before generation because your retriever sees too much • Enforce row-level ACLs → filter before embedding search • Partition vector indexes by tenant → zero cross-org bleed • Sign queries with user identity → audit every retrieval Result: 100% tenant isolation. Zero accidental cross-access — ⚡ The Prompt Injection Trap Insight: A single malicious sentence can override your system prompt. “Ignore previous instructions…” → goodbye guardrails. • Strip tool instructions from retrieved text → no tool hijacking • Freeze system prompts server-side → never client-controlled • Run injection classifier → block risky queries pre-generation Payoff: 80% of jailbreak attempts stopped before inference. — ⚡ The Memory Time Bomb Insight: Long-term memory becomes long-term liability. • Encrypt embeddings at rest → reduce blast radius • Set TTL on conversation memory → auto-expire after 24h • Disable training retention → no vendor data reuse Outcome: Sensitive data lifespan drops from months to hours. — ⚡ The Output Spill Insight: The model can echo secrets it shouldn’t. Especially in summarization and Q&A. • Add regex + NER redaction → mask PII before response • Apply policy LLM pass → secondary compliance filter • Log every response with hash → traceability under 200ms Result: 90% fewer policy violations. — Secure LLM ≠ better prompts. It’s layered defense. Access → Context → Output. 🔖 Save this before your next security review 💬 Comment “SECURE” if you also building safe LLM Appa ➕ Follow for production-grade AI system design breakdowns
🎶 Music Outro 🎶
View Details