How to install and tune oMLX on M5 Max 128 GB
Tested May 2026 recipe: oMLX 0.3.8 on Mac M5 Max with 128 GB, TurboQuant at 3.5-bit, Qwen 3.6 35B-A3B model stack, Claude Code wiring and real benchmarks.
Category
AI without the hype: models, agents and use cases that work in production.
Tested May 2026 recipe: oMLX 0.3.8 on Mac M5 Max with 128 GB, TurboQuant at 3.5-bit, Qwen 3.6 35B-A3B model stack, Claude Code wiring and real benchmarks.
Direct Preference Optimization (DPO) and its variants, IPO, KTO, and SimPO, have displaced RLHF as the preferred alignment method for language models: they drop the separate reward model, cut training cost, and are easier to reproduce. RLHF still has an edge only for frontier models with very large budgets.
The Model Context Protocol, proposed by Anthropic in late 2024 and adopted through 2025-2026 by Anthropic, OpenAI, Google, and the open-source community, already has proven operational patterns: separating generic servers from custom ones, explicit per-tool policies, credentials kept outside the model, prefixed composition, and contract tests. This is the state of the art in 2026.
Using an LLM to judge another LLM became widespread in 2024 and remains, in 2026, the only scalable way to evaluate qualitative quality in LLM systems. It is reliable when judge-human correlation exceeds 0.7 on 30 cases and gets recalibrated quarterly; below that threshold, do not trust the number.
Hybrid RAG in 2026 combines dense and lexical search fused with RRF, cross-encoder reranking over the top-50 candidates, structure-aware chunking, and continuous evaluation with Ragas or TruLens. It is the pattern that survives in serious production systems three years after the initial embeddings boom.
Opus 4.7 launched as Anthropic's most capable model, with emphasis on long-horizon agentic work. After two months of intensive use, these are the practical changes versus Opus 4.6.
While OpenAI and Anthropic dominate headlines with rounds worth hundreds of millions, a growing group of niche AI startups generates one to ten million dollars in revenue with teams of two to ten people. They share five patterns: narrow vertical focus, 70-80% margins, community distribution, iteration cycles in days, and AI as an internal lever.
AI agents fail in production, and what matters is how you respond in the first twenty minutes. This runbook covers severity classification, isolating before investigating, purging contaminated memory, communicating without inventing facts, and turning every incident into a regression test before closing it as done.
Prompt engineering has moved from viral tricks to a discipline with reproducible patterns: few-shot, chain-of-thought, and structured output with function calling. Teams treating prompts like code (versioned, tested, and monitored) get consistently better results than those who improvise.
Durante 2025 cientos de equipos pusieron agentes IA en producción real. A principios de 2026, con datos suficientes, emergen lecciones consistentes sobre qué falla, qué funciona, cuánto cuesta y qué tareas no encajan. Repaso ordenado para equipos que empiezan ahora.
A selection of postmortems published between 2025 and 2026 by teams running AI systems in production reveals repeated patterns: guardrail failures, silent model drift, hidden vendor dependency, and a collection of near-misses worth distilling.
After two years watching every product invent its own interface for talking to an agent, by January 2026 a stable design consensus is emerging about which patterns work, which do not, and what the average user already expects. Time to write down what has settled.