NVIDIA garak Tutorial: Build a Complete Defensive LLM Red-Teaming Workflow with Custom Probes and Detectors
print(“\n########## 5. ANALYSIS ##########”) import numpy as np, pandas as pd def find_latest_report(): cands = [] for base in [os.path.expanduser(“~/.local/share/garak/garak_runs”), os.path.expanduser(“~/.cache/garak”), “.”]: cands += glob.glob(os.path.join(base, “**”, “*report.jsonl”), recursive=True) cands = [c for c in cands if os.path.getsize(c) > 0] return max(cands, key=os.path.getmtime) if cands else None report_path = report_path or find_latest_report() print(“Analysing:”, report_path) evaluations = […]
Google’s New Colab CLI Lets Developers and AI Agents Run Python on Remote Colab GPUs and TPUs From the Terminal
This week, Google AI team released the Colab CLI. The tool connects your local terminal to remote Colab runtimes. It lets developers and AI agents run code on cloud GPUs and TPUs. You stay in your terminal the entire time. The CLI is open source under the Apache 2.0 license. What is Google Colab CLI […]
Picking an Experimentation Platform: A Retrospective
, in every company that wants to ship products people love, when “we should experiment more” becomes “we cannot keep experimenting like this.” Hand-tuned holdouts; traffic-allocation tickets bouncing between PMs and engineers; analyst calendars booked weeks out. The wish to be data-driven sort of outgrows the machinery that was supposed to make it so. That […]
Who Will Win the 2026 Soccer World Cup?
off on June 11 with 48 teams, 104 matches, and the usual avalanche of hot takes. I wanted a forecast I could actually defend. Not just a cool machine learning model with nice results, but a model where every number traces back to an explicit assumption I could argue about. This article builds that forecast […]
My SciPy ODE Solver Was Killing My Bayesian Inference: A Cosmologist’s Honest Account of Discovering Diffrax
The problem that made me look for an alternative . My work involves taking models of the Universe – dark energy equations of state, modified gravity, tachyonic fields – and asking: what do the data actually say about the parameters? The tool for that question is Bayesian inference. I usually run dynesty nested sampling for a few thousand to […]
Moonshot AI Releases Kimi Code CLI: A Terminal AI Coding Agent Built in TypeScript for Next-Gen Agents
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 […]
NVIDIA Releases Nemotron 3.5 ASR: A 600M-Parameter Cache-Aware Streaming Model Transcribing 40 Language-Locales in Real Time
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 […]
A Hands-On Coding Tutorial on Qualcomm AI Hub Models for Classification, Object Detection, and Hardware-Aware Deployment
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 […]
Google DeepMind Releases Gemma 4 QAT Checkpoints: Q4_0 and a New Mobile Format Cut On-Device Memory
Google DeepMind released Quantization-Aware Training (QAT) checkpoints for the Gemma 4 family. The release targets local deployment on edge devices and consumer GPUs. It follows the Gemma 4 launch in April and a 12B model two days earlier. We compared the available Gemma 4 edge-model formats using only published numbers. The goal was simple. Show […]
My AI Couldn’t See My Files — I Built a Zero-Dependency MCP Server
. The functions had grown too long and the variable names made no sense anymore. Every time I wanted feedback on a file, I stopped, opened the chat, copied the whole thing in, and waited. Then went back to the editor, applied the change, opened the next file, and did it again. At some point […]