Fabio Fernandes @safe_number

C++, Multiplatform, hardware, LLMs, Transformers, Streaming, C#, .Net, React, Python Porto, Portugal Joined August 2011

Tweets

1K
Followers

242
Following

1K
Likes

18K

Google for Developers @googledevs

8 hours ago

See how @VetsWhoCode is using the Gemini API to generate personalized learning plans that map veteran skills to current job market demands. Founder and veteran, Jerome Hardaway, shares his approach on the latest People of AI episode. Highlights: 00:00 Introduction to Jerome…

5 12 28 8K 16

Download Video

OpenAI Developers @OpenAIDevs

6 days ago

OpenAI DevDay is in two weeks, then we hit the road. DevDay [Exchange] connects local developers in: São Paulo • Oct 16 London • Oct 21 Bengaluru • Nov 4 Tokyo • Nov 11 Seoul • Nov 13 Spots are limited for these intimate gatherings. Apply: events.openai.com/devdayexchange

26 83 583 51K 94

Download Video

Code Geek @codek_tv

a week ago

Artificial Neuron! Image Credit- Hamed Shah Hosseini

0 5 23 2K 10

Download Image

XM Cyber @XMCyber_

9 months ago

🔒 CFOs: Not just a cost center! Learn how to transform cybersecurity from an expense to a strategic investment. 9 expert tips to get buy-in for CTEM projects and align security with business goals. Read now!

0 6 18 550K 11

Python Space @python_spaces

2 weeks ago

Foundations of LLMs Book for FREE! If you want a FREE copy, 1. Like + Repost 2. Comment 'Python Space' 3. Follow me @python_spaces so that I can DM you.

448 484 2K 150K 1K

Download Image

Matt Pocock @mattpocockuk

2 weeks ago

Most devs think LLM's are only good for producing text. But the real value prop of LLM's is turning raw text/data into structured, searchable objects. If you've never heard of structured outputs, now's your chance:

64 129 2K 209K 2K

Download Video

Krishna Agrawal @Krishnasagrawal

2 weeks ago

Top 10 Database Scaling Techniques 📚📘 Save it for later ... cc : @ashishps_1 #database

13 249 1K 73K 1K

Download Image

Dhanian 🗯️ @e_opore

2 weeks ago

Retrieval-Augmented Generation (RAG) in LLMs Concept → Problem LLMs have fixed knowledge after training and may produce outdated or hallucinated answers. → Solution RAG combines LLMs with external knowledge sources, retrieving relevant documents before generating answers.…

17 164 773 40K 659

Download Image

Python Space @python_spaces

2 weeks ago

Containerized versions of hundreds of MCP servers! MCP Containers provides a toolkit of prebuilt MCP servers with standardized configurations, enabling fast provisioning, streamlined orchestration, and secure lifecycle management. 100% Open source

5 49 250 19K 232

Download Image

Femke Plantinga @femke_plantinga

3 weeks ago

Is your RAG system a paperweight? It is if it can't handle a simple follow-up question. Building basic RAG is easy. The real challenge is engineering systems that go beyond simple retrieval and actually do more with your data. This is how you build a RAG pipeline that can…

20 275 2K 107K 2K

Download Image

Pramod Goyal @goyal__pramod

4 weeks ago

The greatest explanation of PCA you will ever read

10 188 2K 142K 3K

Download Image

Kirk Borne @KirkDBorne

4 weeks ago

[LLM System Design - Part 5] Training the Encoder-Decoder Model — Orchestrating Intelligence — How They Actually Work: naina0405.substack.com/p/important-ll… by @NainaChaturved8

2 18 85 6K 68

Download Image

.NET Foundation @dotnetfdn

4 weeks ago

OData .NET 9 Preview is here—streamlined, secure, and spec-aligned! Targeting #dotnet10, it drops JSONP, defaults to case-insensitive URIs, tightens CSDL validation, and trims payload bloat. Cleaner code, fewer surprises. hubs.li/Q03Gj6770 #dotnet #OSS

1 4 46 3K 21

Download Image

Ian Nuttall @iannuttall

4 weeks ago

OpenAI published a guide on how to use GPT-5 for coding It's similar to most guides, and my semi-hot take 🌶️ is that LLMs are just as good w/ well structured Markdown prompts as they are with XML syntax Main thing with this model is to have very clear instructions! Link below

15 54 481 45K 782

Download Image

apolinario 🌐 @multimodalart

4 weeks ago

we hacked Wan 2.2 and discovered that it does first and last frame filling, works out of the box on 🧨 diffusers i've built an app for it on @huggingface Spaces (which is powering powering our nano banana video mode too 🍌 🎬)

14 65 431 49K 319

Download Video

Jack Morris @jxmnop

a month ago

first i thought scaling laws originated in OpenAI (2020) then i thought they came from Baidu (2017) now i am enlightened: Scaling Laws were first explored at Bell Labs (1993)

51 165 2K 286K 790

Download Image

Wan @Alibaba_Wan

2 months ago

🚀 Introducing Wan2.2: The World's First Open-Source MoE-Architecture Video Generation Model with Cinematic Control! 🔥 Key Innovations: ꔷ World's First Open-Source MoE Video Model: Our Mixture-of-Experts architecture scales model capacity without increasing computational…

86 316 2K 236K 668

Sumanth @Sumanth_077

4 weeks ago

Build and deploy LLM agents just using natural language! AutoAgent is the Fully-Automated & Zero-Code LLM Agent Framework that let's you create and deploy LLM agents using just natural language. 100% Open Source