Blog
1355+ articles — Page 3 of 57
LangWatch Scenario: Stop Vibes-Testing Your AI Agents
At an Amsterdam meetup, the LangWatch team demonstrated Scenario — behavioral testing for AI agents. From vibes-driven pray-and-push to scenario-driven.
Luca Berton •
GitHub Copilot Dev Days Amsterdam: Agentic SDLC and the
Recap of GitHub Copilot Dev Days Amsterdam at TrueFullstaq — live demos of Agentic SDLC, AI-assisted code reviews, incident triage, and the big question.
Luca Berton •
KyvernoCon Virtual 2026: Policy-as-Code Meets AI and
Full agenda and key takeaways from KyvernoCon Virtual 2026 — covering CEL policies, AI workload provenance, ISO27001 compliance, multi-tenant RBAC, GitOps.
Luca Berton •
Book Review: Architecting Generative AI Applications by
A review of Architecting Generative AI Applications (Packt, 2026) covering LLMOps, RAG architectures, agentic systems, and the engineering reality of.
Luca Berton •
Distributed Inference vs Multi-GPU Inference
A practical comparison of multi-GPU inference within a single node versus distributed inference across multiple nodes. Covers tensor parallelism, pipeline.
Luca Berton •
FIO Storage Benchmarks for AI Training: NFS and SMB on
How to benchmark shared storage performance for distributed AI training workloads using FIO on Kubernetes. Covers NFS vs SMB throughput, IOPS patterns.
Luca Berton •
Fine-Tuning Mistral with FSDP and LoRA on OpenShift
A production guide to fine-tuning Mistral models using FSDP2, LoRA/PEFT, and Run:ai on OpenShift with InfiniBand RDMA. Covers NCCL configuration, memory.
Luca Berton •
GenAI-Perf: Benchmarking LLM Inference with NVIDIA's
How to benchmark vLLM inference endpoints using NVIDIA GenAI-Perf from multiple network locations. Covers token throughput, latency percentiles.
Luca Berton •
Multi-Node Distributed Inference with LeaderWorkerSet on
Deploy large language models across multiple Kubernetes nodes using the LeaderWorkerSet (LWS) operator. Covers vLLM pipeline parallelism, NCCL over.
Luca Berton •
Training RetinaNet with DDP on Run:ai: Multi-Node Object
A production guide to training RetinaNet object detection models using PyTorch DDP on Run:ai with Open Images Dataset V7. Covers multi-node orchestration.
Luca Berton •
Inko: The Rust-Compiled Language with Erlang-Style
Inko is a new programming language that compiles to native code via Rust's LLVM backend. It combines single-ownership memory management with Erlang-style.
Luca Berton •
GBrain: Garry Tan's Self-Wiring Knowledge Graph for AI
Y Combinator CEO Garry Tan open-sourced GBrain — a self-wiring knowledge graph that gives AI agents persistent memory. 17,888 pages, hybrid search, entity.
Luca Berton •
Garry Tan's gstack: 23 Claude Code Specialists That Ship
Y Combinator CEO Garry Tan open-sourced gstack — 23 Claude Code slash commands that turn one developer into a virtual engineering team. CEO, designer, QA.
Luca Berton •
Karpathy's CLAUDE.md: 4 Rules That Fix LLM Coding
A single CLAUDE.md file hit #1 on GitHub trending. It encodes Andrej Karpathy's observations about LLM coding failures into 4 behavioral constraints that.
Luca Berton •
Pixi: Building a Package Manager in Rust at RustNL Meetup
Live coverage of Tim de Jager and Bas Zalmstra from prefix.dev presenting Pixi — a fast, cross-platform package manager built in Rust on the conda.
Luca Berton •
Rust in 2026: Why Systems Programming Is Eating the World
Rust adoption is accelerating across Linux kernel, cloud infrastructure, AI frameworks, and developer tools. A practical guide to where Rust delivers the.
Luca Berton •
Rust Async Runtime Deep Dive: Tokio vs async-std vs smol
A production-focused comparison of Rust async runtimes for infrastructure development. Covers Tokio's dominance, when async-std or smol make sense, and.
Luca Berton •
Building CLI Tools in Rust with Clap: From Zero to
Step-by-step guide to building professional CLI tools in Rust using clap, colored output, progress bars, and cross-platform distribution. Includes real.
Luca Berton •
Rust Error Handling Patterns for Production Systems
Practical error handling strategies in Rust for infrastructure code. Covers thiserror vs anyhow, error propagation, retry patterns, and structured error.
Luca Berton •
Rust for Kubernetes Operators: Building Controllers That
How to build production-grade Kubernetes operators in Rust using the kube-rs ecosystem. Covers reconciliation loops, custom resources, error handling, and.
Luca Berton •
Rust Memory Safety Without Garbage Collection: How It Works
A deep dive into Rust's ownership system, borrowing rules, and lifetime annotations. Explains how Rust achieves memory safety at compile time without.
Luca Berton •
Rust vs Go in 2026: Choosing the Right Language for
A practical comparison of Rust and Go for building cloud infrastructure, CLI tools, and distributed systems. Based on real production experience with both.
Luca Berton •
Rust WebAssembly for Cloud Native: Wasm Components in
How Rust and WebAssembly are reshaping cloud-native workloads in 2026. Covers WASI, Wasm Components, Spin/Fermyon, wasmCloud, and when Wasm beats.
Luca Berton •
Writing High-Performance Rust: Zero-Cost Abstractions in
How Rust delivers C-level performance while maintaining high-level abstractions. Covers iterators, monomorphization, inline assembly, SIMD, and profiling.
Luca Berton •