Category
AI without the hype: models, agents and use cases that work in production.
AI agents have moved from a lab curiosity to serious SDKs from three major providers. A reflection on moving from the flashy demo to an internal use case that shifts a real, measurable metric.
Desde que Microsoft abrió GraphRAG, el patrón de usar grafos sobre tus propios datos ha pasado de experimento académico a técnica con aplicaciones prácticas. Reflexión sobre cuándo compensa, cómo se monta y qué errores se repiten.
The AI features Figma has rolled out since Config 2024 are changing how product design teams work. A look at what each feature delivers, what remains human work, and which habits are taking hold across teams.
Con las primeras obligaciones del AI Act europeo ya en vigor, la gobernanza de la IA en empresa deja de ser teórica. Qué comités montar, qué políticas escribir y qué auditar, desde la experiencia de varias implantaciones.
Anthropic publicó Claude 3.7 Sonnet a finales de febrero con pensamiento extendido opcional y un compañero de consola llamado Claude Code. Reflexión sobre qué cambia de verdad y qué queda para la próxima familia.
A year ago open weights were a gamble; today they are a real production option. I review what has worked, what has not, and how Llama, DeepSeek, Qwen, and Mistral are fitting into enterprise architectures that used to depend on closed APIs.
vLLM remains the reference engine for serving LLMs on GPU in 2025: automatic prefix caching sharply cuts latency for repeated prompts, speculative decoding speeds up large models, and multi-LoRA support lowers the cost of multi-tenant SaaS, though multi-GPU support and non-NVIDIA hardware remain weak points.
GraphRAG has been in real enterprise use for over a year: during indexing, an LLM builds a knowledge graph that answers global questions about a corpus well, precisely where classic RAG fails because no single chunk holds the full answer. Here I compare indexing costs, the cases where it pays off, and the hybrid pattern that teams have settled on.
Three years after RLHF became popular, the model-alignment field is far richer. A review of RLHF, DPO, and newer methods such as KTO and ORPO, with criteria for choosing between them.
Google released Gemma 2 in mid-2024, and it has since seen real production use. A look at how it competes in the open-model ecosystem, which sizes actually make sense, and where its adoption has settled in.
o3-mini, the first public release of OpenAI's o3 reasoning series, clearly improves logic, math, and complex code over GPT-4o, though it answers slower and still hallucinates facts. This analysis, based on weeks of real use, explains where it pays off and where it does not.
Google ha lanzado Gemini 2.0 con un énfasis claro en uso de herramientas y agentes. Repaso de qué aporta, dónde está por detrás de la competencia y en qué tipo de aplicaciones encaja mejor.
Two years running AI-assisted code review in a real team leave a clear balance: AI catches mechanical oversights well and writes useful pull-request summaries, but it struggles with architectural judgment and produces many false positives on subtle bugs. The single decision that helped the most was not blocking merges on its automated comments.
Meta publicó Llama 3.2 con modelos tan pequeños como 1B y 3B, pensados específicamente para ejecutarse en dispositivos. Análisis de qué pueden hacer realmente y cómo se comparan con las alternativas.
Qualcomm, Intel and AMD Copilot+ processors have normalised the presence of an NPU in everyday PCs. A 40 TOPS NPU can run quantised Phi-3 Mini drawing just 5-10 W, versus 40-50 W for a laptop GPU doing the same task. What actually changes for running AI models locally, and when it is worth it.
Measuring RAG quality rigorously takes more than skimming a handful of answers: it requires objective metrics (faithfulness, relevance, context precision, and coverage), a golden set of hundreds of curated questions, and regular human validation of the LLM judge to avoid misleading conclusions.
OpenAI presentó o1 en septiembre de 2024. Un modelo que razona internamente antes de contestar. Qué cambia y cuándo merece la pena el coste adicional.
Hybrid search combines BM25 and vector retrieval to cover what each misses alone. Vectors fail on exact identifiers like SKUs or CVEs; BM25 fails when query and document use different vocabulary for the same idea. Reciprocal Rank Fusion (RRF) merges both rankings without depending on their score scales.
llama.cpp is the C++ library that powers Ollama and much of the local-LLM ecosystem. 2024 added speculative decoding with two- to three-fold speedups, an RPC server for sharding layers across machines, and a stable GGUF format. Ollama covers 90% of cases; going direct pays off with uncommon hardware or specific flags.
Ollama became the standard for running large language models locally in 2024. It wraps llama.cpp in a single binary with Docker-style CLI and an OpenAI-compatible API. Phi-3 Mini runs in 4 GB; Llama 3.1 8B Q4 needs 6 GB. For production traffic at scale, vLLM remains the correct choice.
Model Context Protocol (MCP) is the open standard Anthropic published on 25 November 2024 to connect language models with external data and tools over JSON-RPC 2.0. It does not replace function calling: it standardises the server side, aiming to become for context what the Language Server Protocol is for code editors.
Product-market fit for LLM-powered products still depends on the same classic signals: cohort retention, NPS, and revenue expansion. What changes are the higher quality baseline, faster competitor iteration, and where durable moats come from: proprietary data, workflow integration, and network effects.
LLM applications need three distinct observability planes: prompt and response traces for debugging hallucinations, per-token and per-feature cost tracking, and response quality evaluation. Mature tools like Langfuse, LangSmith, and Helicone cover all three planes with specific instrumentation.
TensorRT-LLM is the NVIDIA inference engine that compiles each model into a binary optimized for the exact GPU and batch size it will serve. It uses hand-written CUDA kernels and native FP8 quantization on H100. Against vLLM it can run 2 to 3 times faster in the best case, at the cost of a 30 to 90 minute build.
LoRA cuts fine-tuning cost for large language models by training only small low-rank adaptation matrices instead of every parameter in the base model. QLoRA adds 4-bit quantization on top, cutting required GPU memory by 65-75%, with quality loss of just 1-3% versus full fine-tuning.
Computer Use is the Claude API feature, launched by Anthropic on 22 October 2024, that lets the model view screenshots and move the mouse, type, and click inside a loop your own system executes and controls. It works well on apps without an API and fails on CAPTCHAs, highly dynamic interfaces, and long tasks.
GitHub Copilot Workspace, in technical preview since April 2024, proposes task-oriented development: describe the problem in a GitHub issue and the AI reads the codebase, generates an editable multi-file plan, and implements it. It competes with Cursor Composer, though with more latency; its edge is native integration with PRs, issues, and GitHub history.
OpenAI published Swarm as an experimental, educational framework for multi-agent systems. It reduces coordination to two concepts — agents and handoffs — and fits in under 500 lines of Python. A comparison with CrewAI and LangGraph.
vLLM serves language models on GPU using PagedAttention and continuous batching, two techniques that multiply throughput compared with a naive server. It exposes an OpenAI-compatible API, so migrating an existing application only requires changing the base URL and deploying the right binary.
Claude 3.5 Sonnet (Anthropic, June 2024) matches Claude 3 Opus quality at Sonnet pricing, with a 200k-token context window and 92% on HumanEval. It stands out in coding and complex instruction-following, and introduced the Artifacts workspace feature on Claude.ai.
Mistral Large 2, released by French startup Mistral AI in July 2024, is a 123-billion-parameter model with a 128k-token context window that rivals GPT-4o and Claude 3.5 Sonnet on several benchmarks. Its EU data residency and its 3 EUR per million input tokens pricing make it the most serious European alternative to US providers.
Tras dos años de RAG en producción, patrones claros emergen: chunking inteligente, hybrid search, re-ranking, evaluación continua. Qué evitar.
CrewAI modela agentes como un equipo con roles y tareas. Cómo se compara con LangGraph y AutoGen, y cuándo merece la pena adoptar un patrón multi-agente.
OpenAI's Assistants API offers persistent threads, sandboxed code execution, and managed document search, but OpenAI is shutting it down completely on August 26, 2026 in favor of the Responses API. We look at when it used to pay off against Chat Completions with your own infrastructure, and what to do if your project still depends on it.
The EU AI Act (Regulation 2024/1689) entered force on 1 August 2024. It classifies AI systems into four risk levels with graduated deadlines: prohibitions in February 2025, GPAI obligations in August 2025, and high-risk requirements in August 2026. It applies to any company operating or selling in the EU, with fines exceeding GDPR levels.
Installing Ollama on an Apple Silicon Mac is as simple as running one Homebrew command. Then pick a model based on available RAM (Phi-3 for 8 GB, Llama 3.1 8B for 16 GB) and expose the local, OpenAI-compatible HTTP API on port 11434 to plug it into your own applications.
GitLab Duo brings native AI into the whole devops flow: code completion, chat, MR summaries and vulnerability explanation. Duo Pro costs 19 dollars per user monthly on top of Premium or Ultimate, the same as GitHub Copilot Business. It pays off when your team already lives in GitLab.
Meta released Llama 3.1 405B on July 23, 2024: 405 billion parameters, 128k token context, and benchmarks matching GPT-4o and Claude 3.5 Sonnet. Self-hosting needs about 220 GB of VRAM in Q4; Together.ai, Fireworks, and Groq offer per-token access.
Embeddings retrieve fast but rank poorly. A reranker over the top-100 lifts precision 15–30 %. When it pays off and when it does not.
GPT-4 Turbo, released in November 2023, expanded GPT-4's context to 128,000 tokens and cut the input price threefold, down to 10 dollars per million tokens. GPT-4o now beats it on price, speed and answer quality, but Turbo still holds up in stable production apps, contracts pinned to a specific version, and deterministic tests that depend on its exact behaviour.
Evaluating a RAG system without metrics is pure guesswork. Ragas measures four core signals: faithfulness, answer relevancy, context precision and context recall, using an LLM as judge. TruLens, DeepEval and other frameworks cover similar ground. Wiring evaluation into CI from day one catches regressions in prompts, chunking or model choice before they reach production.
SGLang adds a Python DSL for controlling LLM generation with constrained decoding, parallel branching, and RadixAttention, the structure that indexes the KV cache as a radix trie to reuse shared prefixes across requests. When that pattern exists, speedups over vLLM reach up to 5 times; without it, the advantage shrinks.
GPT-4o is the OpenAI model presented on May 13, 2024, that fuses text, image, and audio into a single native model, without separate pipelines. It delivers roughly 320-millisecond conversational latency, better multimodal understanding, and a price 50% lower than GPT-4 Turbo.
Llama 3 is the open-model family Meta released on April 18, 2024, in 8-billion and 70-billion-parameter sizes, trained on 15 trillion tokens. The 70B beat Claude Sonnet, Mistral Medium, and GPT-3.5 in Meta's own human evaluation, and its licence allows free commercial use up to 700 million monthly active users.
nomic-embed-text-v1.5 from Nomic AI is an embedding model with weights, code and training data released under Apache 2.0: 137 million parameters, up to 8192 tokens of context, and an MTEB score of 62.4, almost matching the 62.3 of OpenAI's text-embedding-3-small, at 768 dimensions instead of 1536.
LangGraph modela agentes LLM como grafos de estados explícitos. Cuándo supera al bucle tradicional de LangChain y cómo estructurar flujos que no se desmoronan en producción.
Outlines, Guidance e Instructor obligan al modelo a emitir JSON válido en el propio paso de generación. Cuándo ganan frente a reintentos y function calling.
Anthropic launched the Claude 3 family on March 4, 2024 with three models: Haiku, Sonnet, and Opus, all with 200k-token context. Haiku costs $0.25 per million tokens; Opus matches GPT-4 Turbo on benchmarks. This comparison explains when to choose each tier and how to combine them in production to cut costs without sacrificing quality where it matters.
Mixtral 8x22B is Mistral AI's Mixture of Experts model released in April 2024: 141B total parameters but only 39B active per token, an unrestricted Apache 2.0 licence, and multilingual performance ahead of Llama 3 70B in Spanish, French, Italian, and German. Production serving needs datacenter-class GPUs.
LM Studio is a desktop app for Mac, Windows, and Linux that downloads and runs large language models on your own machine, with a polished chat interface and no terminal required. It includes an OpenAI-compatible API and RAG with your documents. For individual use it beats Ollama on user experience; for teams or production, OpenWebUI, vLLM, or TGI are the better fit.
A model trained in PyTorch or TensorFlow, running the same way on a server, a phone, a browser tab, or an ARM gateway on the factory floor: that is what ONNX Runtime solves. It turns the ONNX format into a genuinely portable artifact, exported once, at the cost of some peak performance versus a platform-native runtime.
Cuando una aplicación habla con dos o más proveedores de LLM, antes o después aparece un proxy entre medias. LiteLLM propone uno concreto, y esta es la lectura honesta de qué gana y qué cuesta.
Gemini 1.5 Pro launched in February 2024 with a verified one-million-token context window. It retrieves over 95% of data up to 530,000 tokens in recall tests, reshaping RAG system design, making full-document analysis viable, and enabling new architectural patterns through context caching.
Choosing an open LLM for enterprise in 2024 is no longer just Llama 2: Mistral, Mixtral, Qwen, Yi, DeepSeek, and Phi-2 all compete with different licences and sizes. The criteria that actually decide are commercial licence, available hardware, language support, and your own evaluation on real use cases, not just the trendy benchmark.
OpenAI released text-embedding-3 on 25 January 2024 in two variants: small and large. It improves MTEB quality over ada-002, adds variable dimensions you can truncate without retraining, and lowers the price for small. Migration pays off for most serious RAG setups, but measure real recall on your own corpus before reindexing everything.
pgvector matured in 2023-2024 with the HNSW index type and parallel construction that arrived in version 0.6. For projects already running PostgreSQL, a dedicated vector database is not needed in most cases: this guide explains when PostgreSQL is enough, how to configure the index, and where it starts to fall short.
Cohere Embed v3 is an embedding model that distinguishes queries from documents via the input_type parameter and scores intrinsic text quality, with multilingual support for over 100 languages at 1024 dimensions. It costs $0.10 per million tokens versus OpenAI's $0.02, and delivers better recall in multilingual RAG.
Text Generation Inference (TGI) is the Hugging Face stack for serving open LLMs in production: continuous batching, 4-bit and 8-bit quantization, streaming, and an OpenAI-compatible API. After a brief restrictive-licence episode in 2023, it returned to Apache 2.0 in version 2.0.
Claude 2, launched by Anthropic in July 2023, offers a 100,000-token context window and safety grounded in Constitutional AI. Against GPT-4 it wins on long-document analysis and wide-context code; GPT-4 remains ahead on complex mathematical reasoning and its tooling ecosystem.
Vector databases have gone from an experimental curiosity to the central component of most LLM-based products. This comparison covers Qdrant, Pinecone, and Weaviate: architecture, strengths, limitations, and a decision tree for choosing the right option based on your operational priorities and budget.
With quantization, model weights are stored with fewer bits (4, 5, or 8 instead of 16), so Llama 2 13B shrinks from 26 GB to about 7.5 GB. With llama.cpp it runs on an ordinary 16GB-RAM laptop with no dedicated GPU, and the quality loss is smaller than intuition suggests.
pgvector turns PostgreSQL into a fully functional vector database without adding a separate service to the stack. It extends Postgres with the vector type, IVFFlat indexes for approximate nearest-neighbour search (ANN), and the ability to combine relational SQL filters with vector ranking in a single query. For most RAG projects and internal chatbots, those limits never become a problem.
LangChain is a Python framework that unifies building LLM applications: prompt templates, retrievers over vector databases, function-calling agents, and conversational memory. It earns its keep in fast prototypes and multi-model systems, but for a single well-defined production use case, direct code usually stays more maintainable.
A text embedding is a numeric vector that encodes the meaning of a word or phrase, so that semantically similar pieces of text produce nearby vectors measured by cosine distance. The models most used in production are OpenAI ada-002, Sentence Transformers, and BGE, and they mainly serve semantic search, RAG systems, and text classification without training a classic classifier.
Function calling converts the LLM into a component that returns structured data. How it works, real use cases, and common production pitfalls.
Chroma is the easiest vector database to get started with embeddings and semantic search: install it with pip install chromadb, no extra infrastructure required, and it exposes a minimal API (add, query, delete). It suits prototypes and mid-sized RAG systems well; past a few million vectors, Qdrant or Milvus scale better.
Midjourney v5, released in March 2023, delivers consistent photorealism in skin, light, and depth of field, something v4 could not manage. The --style raw parameter disables the default artistic look, ideal for product photography. It still lacks an official API and only runs through Discord, so Stable Diffusion XL and DALL-E 3 remain more practical for automating pipelines.
In 2023, three frameworks address generative AI regulation differently: the EU AI Act sets four risk tiers with fines up to 6% of global turnover; the US NIST framework is voluntary; the UK delegates to sector regulators. Product teams should inventory AI use cases and document risks now.
Ollama makes it trivial to run models like Llama 2 or Mistral on your own computer: one binary, one command, and quantised weights downloading to disk with no compilation required. Covers installation on macOS, Linux, and Windows with an honest look at what local inference can and cannot do compared to frontier models.
Industrial predictive maintenance rarely needs deep learning: classic models such as random forests, SVMs, or survival models solve 80% of cases. The key lies in feature engineering over vibration, temperature, and power-consumption signals, with pipelines that run on as little as 50 MB of RAM without a GPU.
Five months after launch, GPT-4 excels at chained reasoning, technical writing, and medium-complexity code, but still fails at arithmetic, post-cutoff information, and cross-conversation consistency. Claude 2 wins on long context; LLaMA 2 wins on cost and privacy.
Meta released LLaMA 2 on July 18, 2023 with a royalty-free commercial licence, in three sizes (7B, 13B, 70B parameters). The 70B model matches or beats GPT-3.5 on standard benchmarks. For 99.9% of organisations the licence allows download, modification, and production use with full data privacy and no fine-tuning restrictions.
