Category
AI without the hype: models, agents and use cases that work in production.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Google launched Bard in February 2023 with PaLM 2 as its answer to ChatGPT, unveiling the model in May the same year in four sizes: Gecko, Otter, Bison, and Unicorn. PaLM 2 competes with GPT-3.5 and GPT-4 on benchmarks like MMLU and BIG-bench, but Google's real edge is Workspace integration, not the model itself.
Fine-tuning your own LLM pays off in three cases: you need a very specific style or voice, a rigid structured output format, or you want lower cost and latency from a small specialised model. LoRA and QLoRA have cut the GPU cost, but preparing data and running the model in production are still expensive. For everything else, RAG and prompt engineering are usually enough.
ChatGPT plugins let the model invoke external services through an OpenAPI specification. Three months after launch, the ecosystem has around 500 plugins with a clear pattern: they work well for live data lookup and internal API exposure, but show friction in multi-plugin orchestration and real-money transactions.
OpenAI Code Interpreter extends ChatGPT Plus with an isolated Python sandbox: it runs code on demand, reads files you upload (CSV, Excel, PDF, images, ZIPs) and returns results plus charts within the same chat. Sessions are ephemeral and offline, but remarkably effective for exploratory ad-hoc analysis without spinning up a notebook.
DINOv2 is Meta AI's computer vision model, trained via self-supervision on 142 million images with no human labels. With a simple linear layer on the frozen encoder, it matches or beats supervised models on ImageNet classification, semantic segmentation and monocular depth estimation.
An ensemble combines the predictions of several models, through bagging, boosting, or stacking, to reach a more accurate and stable result than any single model. Random Forest and XGBoost dominate tabular data because they exploit that idea: diversity between models reduces error, as long as their mistakes are not correlated with each other.
The step function, or Heaviside function, is the simplest activation function in neural networks: it converts any numeric input into a binary output, 0 or 1, depending on whether it crosses a fixed threshold. It was the central mechanism of Rosenblatt's 1958 perceptron, but because it is not differentiable, it cannot be used in modern backpropagation training.
