World Wire

Moonshot AI has released Kimi Code CLI, an open-source coding agent that runs in the terminal. The tool reads and edits code, runs shell commands, searches files, and fetches web pages. It then chooses its next step based on the feedback it receives. The project is MIT-licensed and lives on GitHub.. Kimi Code CLI is the successor to the older kimi-cli. The new agent is written in TypeScript and distributed via npm. It works out of the box with Moonshot AI’s Kimi models. It can also be configured to use other compatible providers. What is Kimi Code CLI Kimi Code CLI is an AI agent for software development and terminal operations. It can implement new features, fix bugs, and complete refactors. It can also explore an unfamiliar codebase and answer architecture questions. Batch file processing, builds, and chained test runs are supported too. The execution model is feedback-driven. The agent plans steps, modifies code, runs tests, and reports its actions. Read-only ...

NVIDIA’s Nemotron Speech team has released Nemotron 3.5 ASR . It is a 600M-parameter streaming Automatic Speech Recognition (ASR) model. A single checkpoint transcribes 40 language-locales in real time. Punctuation and capitalization are built in natively. The model ships as open weights on Hugging Face. The license is OpenMDW-1.1. The architecture is a Cache-Aware FastConformer-RNNT. What is Nemotron 3.5 ASR Nemotron 3.5 ASR extends nvidia/nemotron-speech-streaming-en-0.6b to many languages. It adds prompt-based language-ID conditioning to the base model. That lets one 600M-parameter checkpoint cover 40 language-locales. No per-language model or model-swapping is required. The model targets two workloads. The first is low-latency streaming for live audio. The second is high-throughput batch transcription. Output is production-ready text with proper casing and punctuation. No separate punctuation-restoration step is needed. Image source: https://ift.tt/csYSlQF ...

In this tutorial, we work through an end-to-end workflow for Qualcomm AI Hub Models . We start by setting up the required package, discovering the available model collection, and loading MobileNet-V2 for local PyTorch inference. We also handle an important input-shape issue by converting NHWC image tensors into the NCHW format expected by the model. From there, we run inference on both the model’s built-in sample input and a real image, inspect top predictions, execute the official Qualcomm AI Hub CLI demo, and extend the workflow with a YOLOv7 object detection example. Also, we include an optional cloud-device section where we compile, profile, and run the model on a real Qualcomm device when an API token is available. Copy Code Copied Use a different Browser import subprocess, sys, os, glob, textwrap, traceback import numpy as np, torch from PIL import Image import matplotlib.pyplot as plt def pip_install(*pkgs): subprocess.run([sys.executable, "-m", "pip...

AI-first development is changing how software gets built. A new approach called “vibe coding” sits at the center of that shift. Developers describe what they want in plain language. An AI agent turns that description into working software. The term was coined by Andrej Karpathy . It captures a move away from line-by-line coding toward natural-language software creation. The developer sets direction and reviews output. The agent handles most of the implementation. It lowers the cost of going from idea to prototype. A founder can test a concept without a full engineering team. An experienced developer can skip boilerplate and focus on architecture. The result is faster iteration and shorter feedback loops. The tools below all support vibe coding workflows. They differ mainly in one trade-off: how much control the developer keeps versus how much the agent automates. Some are full-stack agent platforms that ship live products. Others are AI-native editors that keep ...

In this tutorial, we work with the amphora/ResearchMath-14k dataset, a collection of research-level mathematics problems mined from arXiv. We load the dataset, inspect its structure, and explore how the problems are distributed across mathematical fields and open-status categories. We then move beyond basic analysis by extracting field-specific keywords, generating semantic embeddings, visualizing the problem landscape, clustering related problems, and building a simple search engine over the dataset. Also, we train a classifier to predict problem status from embeddings and detect closely related or near-duplicate problems. Copy Code Copied Use a different Browser !pip -q install -U datasets sentence-transformers scikit-learn umap-learn \ pandas matplotlib seaborn wordcloud 2>/dev/null import warnings, numpy as np, pandas as pd warnings.filterwarnings("ignore") import matplotlib.pyplot as plt import seaborn as sns sns.set_theme(style="whitegrid", palett...