Ded_Coderx
@Ded_Coderx
AI Engineer | Full stack developer | Freelancer building startup based on web3 | Competitive programmer ||
You're in an AI engineer interview at Apple. The interviewer asks: "Siri processes 25B requests/mo. How would you use this data to improve its speech recognition?" You: "Upload all voice notes from devices to iCloud and train a model" Interview over! Here's what you missed:…
This guy literally shows how to build an LLM from scratch in just 6 hours
You're in an ML Engineer interview at Databricks The interviewer asks "Your production chatbot's accuracy was 95% at launch. Six weeks later, user complaints are up and evals show 80%. What do you do?" You reply : "The model is wrong, we need to retrain it." Game over.…
Holy shit… I finally understand the difference between LLMs, RAG, and AI Agents. After building production AI systems for 2 years... Here's what actually matters: They're not competing technologies. They're three layers of the same intelligence stack, and most people are…
Remote jobs are here to stay forever. Replace your 9-5 & achieve freedom while being paid in $. I have prepared a Excel resource that will help you with it. And for 24 hours, it's FREE, just: 1. Follow me (so I can DM you) 2. Like & repost this 3. Reply "Remote"
Build to learn. Then build to make money. Then build to create something new or make an existing thing better, faster. Then build something truly meaningful to you and make the world better. Many people stop at step 2.
Here's a core Linux concept: Why can't you run a Linux binary on Windows, even on the same x86 CPU? You might blame the file format (ELF vs. .exe), but the real answer is the ABI (Application Binary Interface). The ABI is the strict "contract" for how a program "talks" to the…
If you’re learning ML: Don’t chase frameworks Chase intuition Frameworks change Intuition doesn’t #machinelearningengineer #ai
You can make RAG apps 10x smarter with this SOTA method! ColiVara is a retrieval method that does not involve chunking. Instead, it treats docs as images and uses vision models for embedding, just like a human would do. Far better accuracy than traditional RAG systems.
Java: You're trying to understand how some code works. Open a file, it's ~20 lines of trivial boilerplate and getters/setters. Open another, same. And another. And another. This happens like 75 times. It's legitimately hard to find a place where anything is actually being done.
#DeepLearning with PyTorch... 1) Cheat sheet [PDF]: dropbox.com/scl/fi/e4xngyk… 2) Learn fundamentals with hands-on coding [PDF]: dropbox.com/scl/fi/lfo7r6f… 3) #GenerativeAI with Python and PyTorch: amzn.to/4fYjiBn book v/ @PacktDataML
![KirkDBorne's tweet image. #DeepLearning with PyTorch...
1) Cheat sheet [PDF]: dropbox.com/scl/fi/e4xngyk…
2) Learn fundamentals with hands-on coding [PDF]: dropbox.com/scl/fi/lfo7r6f…
3) #GenerativeAI with Python and PyTorch: amzn.to/4fYjiBn book v/ @PacktDataML](https://pbs.twimg.com/media/G5u2B57WYAA4z-n.png)
![KirkDBorne's tweet image. #DeepLearning with PyTorch...
1) Cheat sheet [PDF]: dropbox.com/scl/fi/e4xngyk…
2) Learn fundamentals with hands-on coding [PDF]: dropbox.com/scl/fi/lfo7r6f…
3) #GenerativeAI with Python and PyTorch: amzn.to/4fYjiBn book v/ @PacktDataML](https://pbs.twimg.com/media/G5u2D6cWgAALJU_.jpg)
Agentic RAG didn’t “improve” RAG. It replaced it. And anyone still clinging to vanilla RAG is building with training wheels on. 2023 was the year everyone worshipped simple retrieval pipelines. 2024 exposed the flaw: retrieval is useless if your system can’t think. 2025 is the…
Meta just solved the biggest problem in RAG! Most RAG systems waste your money. They retrieve 100 chunks when you only need 10. They force the LLM to process thousands of irrelevant tokens. You pay for compute you don't need. Meta AI just solved this. They built REFRAG, a new…
Data often lie on a low-dimensional manifold embedded in a high-dimensional space. But these manifolds are often highly non-linear, making linear dimensionality reduction methods like PCA insufficient. This has motivated the development of non-linear dimensionality reduction.
Holy shit... Someone just solved the biggest AI privacy problem nobody talks about. It's called Hyperlink which is a fully offline AI that searches ALL your documents without sending a single byte to the cloud. No OpenAI. No Google. No data leaks. Here's how:↓
We’ve developed a new way to train small AI models with internal mechanisms that are easier for humans to understand. Language models like the ones behind ChatGPT have complex, sometimes surprising structures, and we don’t yet fully understand how they work. This approach…
United States Trends
- 1. Delap 18.3K posts
- 2. Good Saturday 30K posts
- 3. Guiu 9,057 posts
- 4. Burnley 38.3K posts
- 5. GAME DAY 27.6K posts
- 6. Andrey Santos 6,342 posts
- 7. Chelsea 114K posts
- 8. #SaturdayVibes 4,219 posts
- 9. Enzo 36.2K posts
- 10. #Caturday 3,203 posts
- 11. #BURCHE 22.6K posts
- 12. Gittens 9,905 posts
- 13. Maresca 20.1K posts
- 14. Neto 25.7K posts
- 15. Joao Pedro 7,249 posts
- 16. #MeAndTheeSeriesEP2 701K posts
- 17. #askdave N/A
- 18. Dan Lanning N/A
- 19. The View 103K posts
- 20. Chalobah 4,657 posts
Something went wrong.
Something went wrong.