Blog | Roger Oriol

Previous parts of Build a Basic AI Agent From Scratch: Basic Agent Tools Long Task Planning Human in the Loop & Security Security II You can find and clone this code in this blog series' Github repo.

Previous parts of Build a Basic AI Agent From Scratch: Basic Agent Tools Long Task Planning Human in the Loop & Security You can find and clone this code in this blog series' Github repo.

Last week, HuggingFace suffered an AI-assisted cyberattack.

Previous parts of Build a Basic AI Agent From Scratch: Basic Agent Tools Long Task Planning You can find and clone this code in this blog series' Github repo.

Just 3 days after the release of Claude Fable 5 and Mythos 5, Anthropic was forced to suspend access to them by the US Commerce Department.

Anthropic has announced it's most capable model with the name Fable 5.

In the previous part of the Build A Basic AI Agent From Scratch series, we added the essential tools to our agent to allow it to work autonomously for us.

In the previous part of the Build A Basic AI Agent From Scratch series, we built the most basic AI agent harness possible.

2026 is without a doubt the year of AI agents.

It's not at all straightforward to understand the variants of the GPT-5 model released today.

OpenAI has finally released it's GPT-5 model, and as we were already expecting, it's a hybrid reasoning model.

Just like Sam Altman hinted at a while ago, OpenAI just released two open-weight models trying to appease the common criticism of being a company with "Open" in the name that hasn't released any open language models in a long while (since GPT-2!).

While reading Anthropic's great article "How we built our multi-agent research system", I stumbled upon this quote where Anthropic researchers present the results where they found that multi-agent systems outperform single-agents for complex tasks: For ex…

An agent is something that acts in an environment; it does something.

A true AGI must be general across all domains.

There's a new kind of coding I call "hype coding" where you fully give into the hype, and what's coming right around the corner, that you lose sight of whats' possible today.

Together with the launch of the o3 and o4-mini reasoning models, OpenAI has released a coding assitant for the terminal: Codex.

After the unimpressive release of GPT-4.5 a month and a half ago, OpenAI is now releasing a new version - backwards.

Just in the middle of the year of agents, Google has released two great tools for building agents: the Agent2Agent (A2A) protocol and the Agent Development Kit (ADK).

Meta should have made it clearer that “Llama-4-Maverick-03-26-Experimental” was a customized model to optimize for human preference.

Meta has finally released the Llama 4 family of models that Zuckerberg hyped up so much.

A group of Anthropic-affiliated scientists has released a paper where they study how human concepts are represented across Claude 3.5 Haiku's neurons and how these features interact to produce model outputs.

Every web developer has been there: you're starting a new project and staring at an empty file called index.html.

The Anthropic team has discovered an interesting approach to LLM thinking capabilities.

These benchmarks test if AI models can find the right answers to a set of questions we already know the answer to.

On the Internet nobody knows you are a dog... or an LLM The Dead Internet Theory is a thought that has gained a lot of traction recently.

Le Penseur (1904) in the Musée Rodin in Paris.

The past year has been transformative for artificial intelligence, marked by breakthrough innovations, emerging regulations, and a shift toward practical AI tools that enhance productivity.

The recent announcement that Meta's Llama 3.2 Vision models won't be available in the European Union has reignited discussions about the impact of EU regulations on AI innovation and accessibility.

In previous articles, we built a basic RAG application.

In the last article, I established the basic architecture for a basic RAG app.

The dawn of Generative AI makes possible new kinds of capabilities for the applications we build.

One of the tasks Generative AI models are good at is summarizing texts.

Unlike the Transformers architecture, Mixture of Experts is not a new idea.

2023 was a great year for AI.

The problem with LLMs LLMs are very capable to perform a lot of feats that seem incredible to us, but they are bound by the borders of what Generative AI was originally meant to do: generate text based on the data it has been trained on.

LLMs do Natural Language Processing (NLP) to represent the meaning of text as a vector.

Language models have rapidly improved in recent years, with large language models (LLMs) such as GPT-3 and GPT-4 taking center stage.

If you have been using SageMaker Studio, you might have missed some features that other modern IDEs have.

Many enterprises choose a cloud environment to power the work of their data science team.

Painter photo created by rawpixel.com - www.freepik.com A feature store is a storage system for features.

In recent years, the web development landscape has discovered that, while super stylized websites and web applications with tons of very rich interactions made with Javascript might be appealing to users, the loading time of the page can be a hundred times