AiBrain AiBrain
RSS Feedtalking about AI, AGI and vibe coding, with technical and philosophical convictions, while keeping a good dose of common sense and realism.
How LLMs choose their words
Featured
-
Building an Agent: The Art of Assembling the Right Building Blocks
Published: at 10:00 AMPractical guide to building a high-performance AI agent: languages, orchestration, models, telemetry, storage and runtime. The fundamental building blocks.
-
The Onboarding Manual that Turns AI into an Expert: Understanding Agent Skills
Published: at 09:00 AMAnthropic published its Agent Skills specification as an open standard on December 18, 2025. Agent Skills enables transforming a generalist AI into a specialist for your business processes by creating an "onboarding kit" that the AI automatically loads when needed, avoiding repeating the same instructions in every conversation.
-
8 Projectors To Read A Sentence : How an LLM Understands Your Message
Published: at 03:17 PMDiscover how multi-head attention, through the metaphor of 8 projectors, enables ChatGPT and LLMs to decode complex sentence nuances in parallel.
-
End of Transformers? Attention + State-Space Hybrids in 2025
Published: at 10:00 AMThe debate over the announced death of Transformers resurfaces. By late 2025, Attention-SSM hybrid architectures gain ground for efficiency, but pure Transformers still dominate complex reasoning. Reality: coexistence and specialization, not replacement.
-
The Free Transformer: Can Latent Variables Liberate LLMs?
Published: at 10:00 AMMeta's Free Transformer injects latent variables to enable LLMs to make global decisions before generating. Impressive results on reasoning and code, but open questions on scalability.
-
LLMs Put to the Test - Knowledge, Unintentional Cheating, and Abstraction
Published: at 11:00 AMA critical analysis of AI benchmarks and what they truly measure: encyclopedic memory vs abstract intelligence.
-
How AI Giants Sculpt the Soul of Their Virtual Assistants
Published: at 11:00 AMDiscover post-training, the secret art that transforms raw AI models into assistants with distinct personalities.
-
Vibe coding boosts your services
Published: at 12:15 PMA reflection on vibe coding, between technological wonder and forgetting the foundations. Where does the developer stand in this new era?
-
LLMs and web data: how AI collects, filters and uses information.
Published: at 11:00 AMUncover how LLMs access web data: from training datasets to real-time search capabilities and their significant implications for SEO and content strategy.
-
Google Opens the Hood of LLMs
Published: at 11:00 AMDeep dive into Google's groundbreaking publication revealing the internal architecture of large language models and their transformative implications.
-
Draw Me a Sheep on a Motorcycle
Published: at 11:00 AMDive into AI image generation and explore the fascinating challenges of algorithmic creativity. How AI transforms art and pushes creative boundaries today.
Recent Posts
-
arXiv AI Publications - 2025 Week 51
Published: at 11:00 AMTop 5 most relevant AI papers from arXiv Week 51-2025 with analysis and insights.
-
arXiv AI Publications - 2025 Week 50
Published: at 11:00 AMTop 5 most relevant AI papers from arXiv Week 50-2025 with analysis and insights.
-
arXiv AI Publications - 2025 Week 49
Published: at 11:00 AMTop 5 most relevant AI papers from arXiv Week 49-2025 with analysis and insights.
-
arXiv AI Publications - 2025 Week 48
Published: at 11:00 AMTop 5 most relevant AI papers from arXiv Week 48-2025 with analysis and insights.