In this tutorial, we demonstrate a realistic data poisoning attack by manipulating labels in the CIFAR-10 dataset and observing its impact on model behavior. We construct a clean and a poisoned training pipeline side by side, using a ResNet-style convolutional network to ensure stable, comparable learning dynamics. By selectively flipping a fraction of samples from…
OpenAI team has released their openai/circuit-sparsity model on Hugging Face and the openai/circuit_sparsity toolkit on GitHub. The release packages the models and circuits from the paper ‘Weight-sparse transformers have interpretable circuits‘. https://arxiv.org/pdf/2511.13653 What is a weight sparse transformer? The models are GPT-2 style decoder only transformers trained on Python code. Sparsity is not added after…
In this part of the Interview Series, we’ll look at some of the common security vulnerabilities in the Model Context Protocol (MCP) — a framework designed to let LLMs safely interact with external tools and data sources. While MCP brings structure and transparency to how models access context, it also introduces new security risks if…
Google DeepMind has released SIMA 2 to test how far generalist embodied agents can go inside complex 3D game worlds. SIMA’s (Scalable Instructable Multiworld Agent) new version upgrades the original instruction follower into a Gemini driven system that reasons about goals, explains its plans, and improves from self play in many different environments. From SIMA…
Cerebras has released MiniMax-M2-REAP-162B-A10B, a compressed Sparse Mixture-of-Experts (SMoE) Causal Language Model derived from MiniMax-M2, using the new Router weighted Expert Activation Pruning (REAP) method. The model keeps the behavior of the original 230B total, 10B active MiniMax M2, while pruning experts and reducing memory for deployment focused workloads such as coding agents and tool…
Agentic AI browsers are moving the model from ‘answering about the web’ to operating on the web. In 2025, four AI browsers define this space: OpenAI’s ChatGPT Atlas, Microsoft Edge with Copilot Mode, The Browser Company’s Dia, and Perplexity’s Comet. Each makes different design choices around autonomy, memory, and privacy. This article compares their architectures,…
In this tutorial, we explore how to build agentic systems that think beyond a single interaction by utilizing memory as a core capability. We walk through how we design episodic memory to store experiences and semantic memory to capture long-term patterns, allowing the agent to evolve its behaviour over multiple sessions. As we implement planning,…
In 2025, ‘building an AI agent’ mostly means choosing an agent architecture: how perception, memory, learning, planning, and action are organized and coordinated. This comparison article looks at 5 concrete architectures: Hierarchical Cognitive Agent Swarm Intelligence Agent Meta Learning Agent Self Organizing Modular Agent Evolutionary Curriculum Agent Comparison of the 5 architectures Architecture Control topology…
Most text to video models generate a single clip from a prompt and then stop. They do not keep an internal world state that persists as actions arrive over time. PAN, a new model from MBZUAI’s Institute of Foundation Models, is designed to fill that gap by acting as a general world model that predicts…
In this tutorial, we build an advanced interactive dashboard using Textual, and we explore how terminal-first UI frameworks can feel as expressive and dynamic as modern web dashboards. As we write and run each snippet, we actively construct the interface piece by piece, widgets, layouts, reactive state, and event flows, so we can see how…
