André Abrantes

When working with #AI, you need to monitor your GPU metrics while performance tweaking your model parameters (quantization, batch size, multi-threading etc.). On Linux there is already a great CLI tool - nvtop! However, on Windows, the only available tools are GUIs, and Task Manager. Using #VSCode #Copilot, and the latest #dotnet run file.cs feature, I have created a cross-platform performant tool just for this! Check it out: https://lnkd.in/dR5QHFqc

13

1 Comment

What I'm Reading This Week 📚 🚀 Kimi K2 : New Open Source AI's King Moonshot AI released Kimi K2, a 1-trillion parameter open-source model that rivals Claude Opus 4 at coding benchmarks while costing 100x less. Built with a new optimizer architecture and specifically designed for agentic capabilities, it scores well on SWE-bench tests. The pace of frontier-level innovation from Chinese AI labs is remarkable and worth watching closely. https://lnkd.in/gRiinJRW 🧠 Clear Thinking Frameworks Shane Parrish's "Clear Thinking" is a favorite of mine and offers actionable insights on decision-making frameworks, beautifully summarized in this piece. His concept of "position is everything" resonates deeply - choosing what gives you maximum optionality before decisions matter more than perfect decision-making in bad positions. I also recommend his Farnam Street newsletter for weekly mental models that actually stick. Poczwardowski article is a good summary introduction to the book. https://lnkd.in/gA9dbWGm ⚠️ The AI Productivity Reality Check METR's study found that experienced developers using AI tools actually work 19% slower, despite believing they're 20% faster. The culprit: time spent reviewing and correcting AI suggestions that are "directionally correct, but not exactly what's needed." This speaks to the Dunning-Kruger learning curve - like any tool, AI needs mastery to yield impressive results. The perception gap here is fascinating and probably applies beyond just coding. https://lnkd.in/gBY3KRW3 🪟 iPad Windows Growing Pains Craig Hockenberry's analysis of iPadOS 26's new window management reveals a fundamental tension between iOS's 18-year foreground/background model and Mac's 41-year windowing paradigm. Apps aren't syncing properly because Apple engineers are thinking iPhone-first rather than desktop-first. "iOS and iPadOS need that same clear distinction" between app-level and window-level activity states. I'm happy with the progress but these implementation details matter when you're building around the new capabilities. https://lnkd.in/guQszCyn ⚡ Concurrency vs Asynchrony Demystified Loris Cro's deep dive clarifies that asynchrony (tasks running out of order) differs from concurrency (multiple tasks progressing simultaneously). This led me down a rabbit hole learning about Zig, a language with strong opinions about memory management and remarkably clean async/await design. Understanding these distinctions helps me think more clearly about why certain patterns emerge in different contexts. https://lnkd.in/gmtcx8yK #AI #OpenSource #DecisionMaking #Productivity #TechTrends #SoftwareDevelopment #iPadOS

9

We are reimagining PyTorch on TPU (https://lnkd.in/gCrM-TZD). This approach still calls XLA but in a profoundly different way, enabling a solid eager mode. In the limit, this new approach will enable a true JIT approach with recompilation and re-optimization, online feedback-directed optimizations, avoidance of OOMs, support for HW fungibility, hyper-optimizations of kernels, and more - all with close to zero code changes!

341

2 Comments

From Kernel to User Mode: The Ring 3 🦀Lets Run GTA 5 in JC-OS 😎 #RustLang #OsDev #SystemsProgramming #X86_64 #JCOS #TheRustEagle

2

With other colleagues at 🍏, Bruno Mlodozeniec has led a great effort over the second half of 2025 to propose a complete(d) parameterisation for NNs that can achieve the promises of *transferring* local hyperparameter search: tune all optimizers' parameters (e.g. LR) *per module* and *depth* using an evolutionary search with small models, and observe how they transfer successfully out of the box to much larger models, to achieve much better performance with less training budget!

22

1 Comment

Fine-tuning AI shouldn't require thousands of labeled examples. Reinforcement Fine-Tuning (RFT) for Amazon Nova changes that. Just give it prompts + a reward function. The model learns through feedback — not imitation. ✅ No massive datasets ✅ Works for code, customer service, financial reasoning ✅ Runs on Amazon Bedrock, SageMaker, or Nova Forge Smarter customization. Less grunt work. I wrote a deep-dive on this — check out my blog 👇 https://lnkd.in/ggNNezuC Authors:me, along with Chakravarthy Nagarajan Bharathan Balaji Vignesh Radhakrishnan #AWS #GenerativeAI #AmazonNova #MachineLearning #LLM

44

Memory management is one of the biggest challenges AI engineers face today. LLMs are stateless by design, which means every intelligent agent needs a robust memory layer to truly perform in real-world environments. With the introduction of the Redis Agent Memory Server, Redis is tackling this challenge head-on. The open-source solution brings a two-tier memory architecture (working + long-term memory), semantic retrieval, metadata filtering, and asynchronous memory extraction — all built for production scale and speed. It’s a powerful example of how Redis continues to evolve beyond caching into a core infrastructure layer for AI-native applications. If you're building AI agents and thinking about context engineering, persistent memory, and intelligent retrieval, you should explore this! Thank you to Andrew Brookins, Principal Applied AI Engineer, and Raphael De Lio, Developer Advocate at Redis, for sharing this article with us! ➡️ Read the full article on our magazine: https://lnkd.in/db3-fhZT #AI #Redis #AgenticAI #LLMs #DeveloperTools

5

I explored how Spring AI enables tool calling — allowing LLMs to directly execute real-world business logic. This makes it easy to connect your AI agents to live systems like databases, APIs, or even Google Calendar. I’ve also created a short PDF guide summarizing Spring AI Tool Calling — feel free to check it out! 💡 Spring remains the best choice for building enterprise-grade, scalable, and secure AI applications. #SpringAI #Java #AI #LLM #SpringBoot #Developers #EnterpriseAI #OpenAI #ToolCalling

4

Introducing FAI-RL — Roblox’s Open-Source, Reinforcement Learning Library A production-ready, easy-to-use, and config-driven framework for fine-tuning LLM using reinforcement learning. ✨ Key Features: - Implements RL algorithms—DPO, PPO, GRPO, GSPO—plus Supervised Fine-Tuning support. - Includes benchmark evaluation datasets: MMLU & GSM8K. - Highly extensible: Custom reward functions, dataset templates, and API integrations. Designed for researchers and engineers who need a flexible and scalable solution for LLM fine-tuning 🔗 GitHub: https://lnkd.in/gMnS2XhW Try it out and looking forward to your feedback!

44