Categories
Jacar categories — explore the topics A rocket whose eyes follow your cursor.

Category

Artificial Intelligence

AI without the hype: models, agents and use cases that work in production.

Artificial Intelligence
View Cards
Mode Paginated
Per page Per batch 72
Clear filters
Artificial Intelligence

Mature LLM-as-judge: when to trust and when not

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.

2 min 286 4.7
Architecture

Hybrid RAG in 2026: the patterns that keep winning

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.

3 min 537 4.6
Artificial Intelligence

Profitable niche AI startups: the patterns that repeat

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.

4 min 474 4.7
Artificial Intelligence

DPO and alternatives to RLHF: practical state in 2026

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.

3 min 1.2K 4.6
Architecture

MCP as multi-vendor standard: patterns already mature

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.

3 min 306 4.5
Artificial Intelligence

AI agent incidents: recovery runbooks that work

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.

4 min 235 4.7
Artificial Intelligence

Prompt Engineering: From Trick to Mature Discipline

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.

5 min 271 4.7
Artificial Intelligence

UX for agents: first design consensus

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.

7 min 310 4.5
Artificial Intelligence

Phi-3 on the edge: Microsoft’s SLM in 2025

Phi-3 es la familia de modelos pequeños de lenguaje que Microsoft viene puliendo desde abril de 2024 con variantes de 3.800 millones, 7.000 millones y 14.000 millones de parámetros. Después de año y medio, el panorama del edge con SLM abiertos se ha vuelto serio y Phi-3 ocupa un sitio claro.

5 min 273 4.6
Architecture

Agent OS: the concept shaping the new stack layer

The term Agent OS has spent a year gaining traction across research and product circles. It describes a layer that goes well beyond an agent library: request scheduling, context management, persistent memory, and isolation. A look at the real state of that concept.

5 min 298 4.5
Artificial Intelligence

The knowledge graph era is reborn with LLMs

For a decade, knowledge graphs were an academic idea with few real use cases, held back by the cost of building and maintaining the schema. LLMs have changed that equation: they now extract entities automatically and help anchor answers, audit reasoning, and support agents without hallucinating.

5 min 250 4.5
Architecture

Applying graph RAG to a real product

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.

6 min 253 4.7
Artificial Intelligence

NPU in the PC: faster, cheaper local AI

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.

5 min 223 4.5
Architecture

Model Context Protocol: Anthropic’s Open Proposal

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.

6 min 267 4.6
Artificial Intelligence

Mistral Large: European Contender Against GPT-4

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.

5 min 225 4.7
Artificial Intelligence

GPT-4 Turbo: Long Context and More Reasonable Costs

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.

4 min 210 4.6
Artificial Intelligence

Retrieval Evaluation Frameworks: Ragas and Similar

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.

5 min 207 4.6
Artificial Intelligence

Claude 3 Family: Haiku, Sonnet and Opus Compared

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.

3 min 233 4.5
Artificial Intelligence

LM Studio: Exploring AI Models from Your Desktop

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.

3 min 216 4.6
Artificial Intelligence

OpenAI text-embedding-3: What Changes vs the Previous One

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.

4 min 229 4.5
Artificial Intelligence

Claude 2: Anthropic’s Alternative to GPT-4

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.

4 min 195 4.5
Artificial Intelligence

Model Quantization and llama.cpp on Your Laptop

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.

5 min 258 4.5
Artificial Intelligence

Text Embeddings: Turning Words Into Useful Vectors

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.

5 min 258 4.8
Artificial Intelligence

LLaMA 2 and the New Wave of Open Language Models

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.

4 min 235 4.6
Artificial Intelligence

Bard and PaLM 2: Google’s Bet on Generative AI

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.

4 min 287 4.5
Artificial Intelligence

LLM Fine-Tuning: When It’s Worth Training Your Own

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.

4 min 257 4.6
Artificial Intelligence

ChatGPT With Plugins: An Ecosystem Under Construction

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.

5 min 216 4.7
Artificial Intelligence

OpenAI Code Interpreter: Conversational Data Analysis

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.

4 min 249 4.6
Artificial Intelligence

DINOv2: Advances in Self-Supervised Computer Vision

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.

4 min 253 4.5
Artificial Intelligence

Ensemble Learning in Machine Learning

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.

6 min 313 4.7
Artificial Intelligence

The Step Function: An Essential Tool in Neural Networks

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.

3 min 352 4.5
Artificial Intelligence

B2B Sales Optimisation with AI

AI optimises B2B sales through four levers: predictive lead scoring that prioritises the buyers most likely to close, conversation analysis, at-scale outreach personalisation and automating repetitive tasks. Its real impact depends on starting from clean CRM data.

5 min 182 4.5
Artificial Intelligence

Federated Learning and Privacy: Data Protection

Federated learning trains AI models collaboratively across many devices or organisations without moving the original data: each participant trains locally and sends only gradients to the central server. Formalised by Google in 2016, it does not guarantee privacy on its own: it needs differential privacy or secure aggregation to prevent leaks from those gradients.

5 min 173 4.5
Artificial Intelligence

Robotics and Intelligent Automation: The New Industrial Era

Intelligent automation combines AI, machine learning, and physical robots that perceive, decide, and adapt in real time instead of following a fixed script. It is transforming manufacturing, logistics, healthcare, and food processing, and by 2024 there were already more than 4.6 million industrial robots active worldwide, per the IFR.

5 min 175 4.5
Artificial Intelligence

Image Analysis: Computer Vision

Computer vision is the branch of artificial intelligence that lets machines interpret digital images: detecting objects, segmenting regions and recognising patterns through convolutional neural networks. Since 2012, when AlexNet cut ImageNet classification error to 15.3%, it has spread into manufacturing, medicine, transport and precision agriculture.

5 min 224 4.7
Artificial Intelligence

NLP Advances: The Technology Revolutionising Language Processing

Natural Language Processing (NLP) is the AI discipline that enables machines to understand, interpret, and generate human text and speech. Powered by the transformer architecture since 2017, NLP drives chatbots, automatic translation, and clinical diagnosis tools, with open challenges in causal reasoning, energy efficiency, and bias mitigation.

4 min 211 4.5