Artificial intelligence
-
Coding, A Data-Driven Guide to Measuring, Visualizing, and Enforcing Cognitive Complexity in Python Projects Using complexipy
In this tutorial, we build a complex end-to-end analytics workflow using complexipy. We start by measuring the complexity directly from…
Read More » -
Anthropic Claude Opus 4.6 Release With 1M Context, Agentic Code, Adaptive Logical Controls, and Expanded Security Tools Capabilities
Anthropic introduced Claude Opus 4.6, its most powerful model to date, focusing on long-range content visualization, agent coding, and high-value…
Read More » -
Helping AI agents search for the best results in large language models | MIT News
Whether you’re a scientist putting together research ideas or a CEO hoping to automate human resources or finance, you’ll find…
Read More » -
OpenAI Just Launched GPT-5.3-Codex: An Accelerated Model for Agentic Coding That Combines Frontier Code Performance And Expert Consulting In A Single System
OpenAI recently introduced GPT-5.3-Codex, a new agent coding model that extends Codex from writing and updating code to handling a…
Read More » -
Mistral AI Introduces Voxtral Transcribe 2: Pairing a Diarization Cluster and Enabling Real-Time ASR for Multilingual Production Workloads at Scale
Automatic speech recognition (ASR) is becoming the foundation for building AI products, from conferencing tools to voice agents. The new…
Read More » -
NVIDIA AI Releases VibeTensor: AI Generated Deep Learning Time Built to End Programming Coding Agents
NVIDIA released VIBETENSOR, an open source research system stack for deep learning. VIBETENSOR is produced by LLM’s powerful coding agents…
Read More » -
How to Build Effective Agent Thinking Methods by Dynamically Pruning Multiple Thinking Methods Without Losing Accuracy
In this tutorial, we use a chain logic pruning framework that generates multiple logics in parallel and dynamically reduces them…
Read More » -
Google Introduces Agentic Vision in Gemini 3 Flash for Active Image Understanding
Frontier multimodal models typically process an image in a single pass. If they miss a serial number on a chip…
Read More » -
Brian Hedden named associate director of Computer Social and Ethical Responsibilities | MIT News
Brian Hedden PhD ’12 has been named associate director of the Social and Ethical Responsibilities of Computing (SERC) at MIT,…
Read More » -
Implementation of Coding to Train Agents for Offline Security Reinforced Priority Learning Using Conservative Q-Learning with d3rlpy and Embedded Historical Data
In this tutorial, we build a security-enhancing learning pipeline that learns entirely from static, offline data rather than live testing.…
Read More »