Latest in AI

In this tutorial, we implement a hands-on workflow for NVIDIA cuTile Python, a tile-based GPU programming interface for CUDA-style kernels in Python. We prepare a Colab-friendly environment and check GPU, driver, CUDA, and cuTile availability before running kernels. We then build tiled vector addition, matrix addition, and matrix multiplication, keeping a PyTorch fallback so the notebook stays executable. We validate correctness against PyTorch and benchmark median runtimes at every stage.

The post NVIDIA cuTile Python Tutorial: Building Tiled GPU Kernels for Vector Addition, Matrix Addition, and Matrix Multiplication in Colab appeared first on MarkTechPost.

A new Harvard and Perplexity paper uses matched-pair sessions to compare an autonomous agent with a search assistant. It finds large gains in autonomy, time, and cost, plus broader scope of work attempted.

The post A New Study from Harvard and Perplexity Finds AI Agents Perform 26 Minutes of Autonomous Work per Session vs 33 Seconds for Search appeared first on MarkTechPost.

In this tutorial, we explore the ClawHub Security Signals dataset to see how scanners assess AI skills. We load the data from the Hugging Face Parquet conversion and inspect verdicts, scanner outputs, and severity labels. We measure how VirusTotal, static analysis, and SkillSpector overlap and disagree using Jaccard scores and Cohen's kappa. Finally, we combine SKILL.md text with scanner signals to train a logistic regression model for ClawScan verdicts.

The post ClawHub Security Signals: A Coding Guide to End-to-End Security Signal Analysis and Verdict Classification on the AI Skills Dataset appeared first on MarkTechPost.

Xiaomi's MiMo team, with TileRT, released MiMo-V2.5-Pro-UltraSpeed, a serving mode for the MiMo-V2.5-Pro model. It decodes over 1000 tokens per second on a 1-trillion-parameter model using a single 8-GPU commodity node.

The post Xiaomi MiMo and TileRT Push a 1-Trillion-Parameter Model Past 1000 Tokens Per Second on Commodity GPUs appeared first on MarkTechPost.

Microsoft AI has released MAI-Transcribe-1.5, the second iteration of its in-house speech-to-text family. The model covers 43 languages, adds keyword (entity) biasing for domain-specific terms, posts a 2.4% Word-Error-Rate on the Artificial Analysis leaderboard, and transcribes an hour of audio in under 15 seconds. It is generally available in Azure AI Foundry.

The post Microsoft AI Introduces MAI-Transcribe-1.5: 2.4% WER on Artificial Analysis, Best-in-Class FLEURS Accuracy, and Up to 5x Faster Long-Audio Transcription appeared first on MarkTechPost.

Google Research details an agentic RAG framework in Gemini Enterprise Agent Platform. A Sufficient Context Agent re-searches until multi-hop, multi-source queries have enough grounding to answer. The framework raises factuality accuracy up to 34% versus standard RAG.

The post Google Research Adds Agentic RAG to Gemini Enterprise Agent Platform with a Sufficient Context Agent for multi-hop queries appeared first on MarkTechPost.

In this tutorial, we use GEPA as a reflective prompt-evolution framework to improve how a small language model solves multi-step arithmetic word problems. We start from a weak seed prompt, build a deterministic benchmark, and define a structured evaluator that returns actionable feedback. A multi-component setup evolves both the instruction field and the output-format rules together. We then compare the baseline and optimized prompts on a held-out validation set to check whether the gains generalize.

The post Building Reflective Prompt Optimization with GEPA: Multi-Component Prompts, Structured Feedback, and Held-Out Validation appeared first on MarkTechPost.

Low-code and no-code AI platforms now turn a prompt into a working app, agent, or model. This guide compares 21 tools across app builders, automation, AI agents, and machine learning platforms, each linked to its official site.

The post Best 21 Low-Code and No-Code AI Tools in 2026 appeared first on MarkTechPost.

UIUC and Chroma's Harness-1 is a 20B retrieval subagent trained with reinforcement learning inside a stateful search harness. The harness maintains the bookkeeping — candidate pool, importance-tagged curated set, evidence graph, verification records — while the policy decides what to search, curate, verify, and when to stop. It reaches 0.730 average curated recall across eight benchmarks, beating the next open subagent by 11.4 points and trailing only Opus-4.6. Weights and harness code are public.

The post Meet Harness-1: A 20B Retrieval Subagent Trained With Reinforcement Learning Inside a Stateful Search Harness on gpt-oss-20b appeared first on MarkTechPost.

This tutorial walks through NVIDIA garak as an end-to-end framework for defensive LLM red-teaming. It covers setup, plugin discovery, dry runs, real-model scans on a Hugging Face generator, and multi-probe evaluations. The workflow then analyzes safety scores and attack success rates, inspects flagged outputs, and extends garak with a custom probe and detector. It closes by exporting results in AVID format for structured vulnerability

The post NVIDIA garak Tutorial: Build a Complete Defensive LLM Red-Teaming Workflow with Custom Probes and Detectors appeared first on MarkTechPost.

Google released the Colab CLI, letting developers and AI agents run local code on remote Colab GPU and TPU runtime

The post Google’s New Colab CLI Lets Developers and AI Agents Run Python on Remote Colab GPUs and TPUs From the Terminal appeared first on MarkTechPost.

Kimi Code CLI is Moonshot AI's open-source terminal coding agent, written in TypeScript with subagents and MCP configuration.

The post Moonshot AI Releases Kimi Code CLI: A Terminal AI Coding Agent Built in TypeScript for Next-Gen Agents appeared first on MarkTechPost.

NVIDIA released Nemotron 3.5 ASR, a cache-aware 600M streaming model transcribing 40 language-locales in real time from one checkpoint.

The post NVIDIA Releases Nemotron 3.5 ASR: A 600M-Parameter Cache-Aware Streaming Model Transcribing 40 Language-Locales in Real Time appeared first on MarkTechPost.

Set up Qualcomm AI Hub Models to run MobileNet-V2 inference, YOLOv7 detection, and compile models on real devices.

The post A Hands-On Coding Tutorial on Qualcomm AI Hub Models for Classification, Object Detection, and Hardware-Aware Deployment appeared first on MarkTechPost.

Compare Gemma 4 edge formats: BF16, Q4_0 QAT, and mobile QAT, on published memory numbers and design tradeoffs.

The post Google DeepMind Releases Gemma 4 QAT Checkpoints: Q4_0 and a New Mobile Format Cut On-Device Memory appeared first on MarkTechPost.

NVIDIA Dynamo Snapshot checkpoints and restores vLLM inference workers on Kubernetes using CRIU and cuda-checkpoint tools.

The post NVIDIA AI Releases Dynamo Snapshot: A CRIU-Based Fast Startup System for AI Inference on Kubernetes appeared first on MarkTechPost.

Perplexity AI announces a hybrid local-server inference orchestrator for Personal Computer, automatically routing AI tasks between on-device and cloud models.

The post Perplexity AI Introduces Hybrid Local-Server Inference Orchestrator for Personal Computer: Automatic On-Device and Cloud Task Routing appeared first on MarkTechPost.

A hands-on guide to running Microsoft Fara in Colab, testing the browser agent loop with a mock endpoint.

The post Microsoft Fara Tutorial: Run a Browser-Use Agent in Google Colab with a Mock OpenAI-Compatible Endpoint appeared first on MarkTechPost.

Vibe coding turns plain language into working software. Explore 15 tools shaping how developers build apps in 2026.

The post 15 Best Vibe Coding Tools in 2026 Compared: Pricing, Features, and Best Fit appeared first on MarkTechPost.

This tutorial walks through a complete NLP pipeline for research-level mathematics. Using the ResearchMath-14k dataset, we extract field-specific keywords with TF-IDF, generate sentence embeddings, visualize the problem landscape with UMAP, cluster with K-Means, build a semantic search engine, and train a classifier to predict each problem's open status — then surface near-duplicate problems by similarity.

The post Building a Semantic Search Engine and Open-Status Classifier over the ResearchMath-14k Dataset appeared first on MarkTechPost.