In this tutorial, we implement a dual-agent governance system that applies Constitutional AI principles to financial operations. We demonstrate how we separate execution and oversight by pairing a Worker Agent that performs financial actions with an Auditor Agent that enforces policy, safety, and compliance. By encoding governance rules directly into a formal constitution and combining rule-based checks with AI-assisted reasoning, we can build systems that are self-reflective, auditable, and resilient to risky or non-compliant behavior in high-stakes financial workflows. Check out the FULL CODES here. !pip install -q pydantic anthropic python-dotenv import json import re from typing import List, Dict, Any,…

Qwen3-Max-Thinking is Alibaba’s new flagship reasoning model. It does not only scale parameters, it also changes how inference is done, with explicit control over thinking depth and built in tools for search, memory, and code execution. https://qwen.ai/blog?id=qwen3-max-thinking Model scale, data, and deployment Qwen3-Max-Thinking is a trillion-parameter MoE flagship LLM pretrained on 36T tokens and built on the Qwen3 family as the top tier reasoning model. The model targets long horizon reasoning and code, not only casual chat. It runs with a context window of 260k tokens, which supports repository scale code, long technical reports, and multi document analysis within a…

Can a fully sovereign open reasoning model match state of the art systems when every part of its training pipeline is transparent. Researchers from Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) release K2 Think V2, a fully sovereign reasoning model designed to test how far open and fully documented pipelines can push long horizon reasoning on math, code, and science when the entire stack is open and reproducible. K2 Think V2 takes the 70 billion parameter K2 V2 Instruct base model and applies a carefully engineered reinforcement learning approach to turn it into a high precision reasoning model that…

Tencent Hunyuan has open sourced HPC-Ops, a production grade operator library for large language model inference architecture devices. HPC-Ops focuses on low level CUDA kernels for core operators such as Attention, Grouped GEMM, and Fused MoE, and exposes them through a compact-C and Python API for integration into existing inference stacks. HPC-Ops runs in large scale internal services. In those deployments it delivers about 30 percent queries per minute improvement for Tencent-HY models and about 17 percent improvement for DeepSeek models on mainstream inference cards. These gains are reported at the service level, so they reflect the cumulative effect of…

Moonshot AI has released Kimi K2.5 as an open source visual agentic intelligence model. It combines a large Mixture of Experts language backbone, a native vision encoder, and a parallel multi agent system called Agent Swarm. The model targets coding, multimodal reasoning, and deep web research with strong benchmark results on agentic, vision, and coding suites. Model Architecture and Training Kimi K2.5 is a Mixture of Experts model with 1T total parameters and about 32B activated parameters per token. The network has 61 layers. It uses 384 experts, with 8 experts selected per token plus 1 shared expert. The attention…

In this tutorial, we implement Tree-KG, an advanced hierarchical knowledge graph system that goes beyond traditional retrieval-augmented generation by combining semantic embeddings with explicit graph structure. We show how we can organize knowledge in a tree-like hierarchy that mirrors how humans learn, from broad domains to fine-grained concepts, and then reason across this structure using controlled multi-hop exploration. By building the graph from scratch, enriching nodes with embeddings, and designing a reasoning agent that navigates ancestors, descendants, and related concepts, we demonstrate how we can achieve contextual navigation and explainable reasoning rather than flat, chunk-based retrieval. Check out the FULL CODES…

Data science agents should inspect datasets, design workflows, run code, and return verifiable answers, not just autocomplete Pandas code. DSGym, introduced by researchers from Stanford University, Together AI, Duke University, and Harvard University, is a framework that evaluates and trains such agents across more than 1,000 data science challenges with expert curated ground truth and a consistent post training pipeline. https://arxiv.org/pdf/2601.16344 Why existing benchmarks fall short? The research team first probe existing benchmarks that claim to test data aware agents. When data files are hidden, models still retain high accuracy. On QRData the average drop is 40.5 percent, on DAEval…

@tool def sql_investigate(query: str) -> dict: try: df = con.execute(query).df() head = df.head(30) return { "rows": int(len(df)), "columns": list(df.columns), "preview": head.to_dict(orient="records") } except Exception as e: return {"error": str(e)} @tool def log_pattern_scan(window_start_iso: str, window_end_iso: str, top_k: int = 8) -> dict: ws = pd.to_datetime(window_start_iso) we = pd.to_datetime(window_end_iso) df = logs_df[(logs_df["ts"] >= ws) & (logs_df["ts"] <= we)].copy() if df.empty: return {"rows": 0, "top_error_kinds": [], "top_services": [], "top_endpoints": []} df["error_kind_norm"] = df["error_kind"].fillna("").replace("", "NONE") err = df[df["level"].isin(["WARN","ERROR"])].copy() top_err = err["error_kind_norm"].value_counts().head(int(top_k)).to_dict() top_svc = err["service"].value_counts().head(int(top_k)).to_dict() top_ep = err["endpoint"].value_counts().head(int(top_k)).to_dict() by_region = err.groupby("region").size().sort_values(ascending=False).head(int(top_k)).to_dict() p95_latency = float(np.percentile(df["latency_ms"].values, 95)) return { "rows": int(len(df)), "warn_error_rows": int(len(err)), "p95_latency_ms": p95_latency, "top_error_kinds": top_err,…

For decades, predicting the weather has been the exclusive domain of massive government supercomputers running complex physics-based equations. NVIDIA has shattered that barrier with the release of the Earth-2 family of open models and tools for AI weather and climate prediction accessible to virtually anyone, from tech startups to national meteorological agencies. In a move that democratizes climate science, NVIDIA unveiled 3 groundbreaking new models powered by novel architectures: Atlas, StormScope, and HealDA. These tools promise to accelerate forecasting speeds by orders of magnitude while delivering accuracy that rivals or exceeds traditional methods. The Democratization of Weather Intelligence Historically, running…

Clawdbot is an open source personal AI assistant that you run on your own hardware. It connects large language models from providers such as Anthropic and OpenAI to real tools such as messaging apps, files, shell, browser and smart home devices, while keeping the orchestration layer under your control. The interesting part is not that Clawdbot chats. It is that the project ships a concrete architecture for local first agents, and a typed workflow engine called Lobster that turns model calls into deterministic pipelines. Architecture: Gateway, Nodes and Skills At the center of Clawdbot is the Gateway process. The Gateway…