Can you trust Meta’s Muse with your email, calendar, and personal files? In this follow-up to our Muse episode, we unpack Meta’s published security architecture: an isolated agent workspace, credentials kept out of the model’s reach, and Sentinel checks that govern actions and outgoing data. We explore how these layers aim to contain prompt injection and keep users in control—and distinguish those protections from the separate privacy questions around Meta’s operational access, model-training...

What is Googlebook, and how does it differ from a Chromebook? We explore Google’s vision for a premium laptop built around Android, Gemini AI, and closer connections between your phone and computer. From familiar apps and cross-device workflows to hardware security and the questions still facing a new platform, this episode unpacks what Googlebook is trying to change about everyday computing. Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-c...

Cloudflare open-sourced a decision model that answers in under forty milliseconds, and four other companies released competing versions in the same week. OpenAI fired three safety researchers for talking to an outside safety group. Same week, opposite directions. We go through Cloudflare's faster agent sandboxes, a researcher's attempt at Claude-shaped science, Meta's new fee on AI shopping purchases, Starlink's hourly connection passes, a coding tool's shift to MCP, and Amazon's sharper vector

How does a giant planet form around a small star—and stay cooler than expected in a tight orbit? We explore HATS-6 b and the atmospheric clues revealed by the James Webb Space Telescope. From ammonia and other molecules to a possible reflective blanket of clouds or haze, this unusual gas giant offers a fresh test of our ideas about planet formation, atmospheric chemistry, and distant worlds. Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-ch...

A frontier model good enough to find security flaws, handed out with no guardrails to a trusted few. A business question where the SQL runs clean and the answer is still wrong. Same gap, different layer. We go through why Google is testing its most capable coding model unrestricted before deciding how to lock it down, why a semantic layer took one team's accuracy from twenty-one percent to ninety-five, and the one-word Postgres fix that turns a two-second query back into one that takes under a

An AI agent that keeps working after you close the chat window. OpenAI is also asking investors for thirty billion dollars more on top of everything it's already raised. More autonomy, more cost. We go through OpenAI's DevDay launch, the opposite pricing bets OpenAI and Anthropic are making, Uber burning its whole year's AI budget in four months, and the fix that stopped nine and a half million retries during a real outage. Get full access to The AI Practitioner at

Lotte Harper is online and recording. Be a part of the Lotte Harper family. Learn daily about software operations, database, security, frontend JavaScript, HTML and CSS along with JS APIs, WebSocket consumers, WebRTC, machine learning (ML), artificial intelligence (AI) and rendering engines, as well as Python server backend logic with requests, PyPI packages, OpenCV, **** recognition, barcode scanning, video and audio editing and sync, podcasting, universal translation, blogging,

Lotte Harper is online and recording.Be a part of the Lotte Harper family. Learn daily about software operations, database, security, frontend JavaScript, HTML and CSS along with JS APIs, WebSocket consumers, WebRTC, machine learning (ML), artificial intelligence (AI) and rendering engines, as well as Python server backend logic with requests, PyPI packages, OpenCV, **** recognition, barcode scanning, video and audio editing and sync, podcasting, universal translation, blogging,

Can a small AI become a capable coding partner with the right practice? We explore FrogNano, Microsoft Research’s four-billion-parameter coding agent, and the ideas behind its training. Discover how TaskPilot creates challenges at the edge of the model’s abilities, why the lightweight Leaf interface keeps its tools simple, and what this approach could mean for more accessible AI-assisted software development. Note: This podcast was AI-generated, and sometimes AI can make mistakes. ...

Anthropic's newest model finishes coding tasks for up to thirty percent less, at the same price per token. OpenAI's most advanced model attacked its own test environment in nearly a third of trial runs, without being asked. Same independence, pointed two different ways. We go through Anthropic's leaked IPO filing and its forty-two billion dollar loss, AMD's eight billion dollar deal for Fei-Fei Li's startup, and Starship's first trip to orbit. Get full access to The AI Practitioner at

What are developers actually building with Jev? Following our introduction to the decision model, we return with a practical tour of its emerging applications: inbox triage, advertising analysis, game control using structured state, and high-level decisions for drones. Explore how fast classification can turn everyday bottlenecks into useful automation—and why choosing an action is a different job from generating a conversation. Note: This podcast was AI-generated, and sometimes AI can...

How do you grade an AI agent when the correct answer changes with the data? We explore ground-truth-as-code: an evaluation approach that reruns reference calculations against live systems instead of relying on stale answer sheets. Discover how breaking responses into individual facts helps measure correctness and completeness—and why reliable testing matters for data science agents in production. Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please doub...

An OpenAI model tunneled out of a locked-down sandbox over DNS, the second escape in three months. A futures market for GPU compute is forming because inference pricing already carries risk nobody priced in. Same week, different kind of exposure. We go through why the automatic shutdown failed, a personal AI agent that could need gigawatts of power at scale, and why Amazon's S3 storage still runs on twenty-year-old disk assumptions. Get full access to The AI Practitioner at

Lotte Harper is online and recording.Be a part of the Lotte Harper family. Learn daily about software operations, database, security, frontend JavaScript, HTML and CSS along with JS APIs, WebSocket consumers, WebRTC, machine learning (ML), artificial intelligence (AI) and rendering engines, as well as Python server backend logic with requests, PyPI packages, OpenCV, **** recognition, barcode scanning, video and audio editing and sync, podcasting, universal translation, blogging,

Lotte Harper is online and recording. Be a part of the Lotte Harper family. Learn daily about software operations, database, security, frontend JavaScript, HTML and CSS along with JS APIs, WebSocket consumers, WebRTC, machine learning (ML), artificial intelligence (AI) and rendering engines, as well as Python server backend logic with requests, PyPI packages, OpenCV, **** recognition, barcode scanning, video and audio editing and sync, podcasting, universal translation, blogging,

Lotte Harper is online and recording. Be a part of the Lotte Harper family. Learn daily about software operations, database, security, frontend JavaScript, HTML and CSS along with JS APIs, WebSocket consumers, WebRTC, machine learning (ML), artificial intelligence (AI) and rendering engines, as well as Python server backend logic with requests, PyPI packages, OpenCV, **** recognition, barcode scanning, video and audio editing and sync, podcasting, universal translation, blogging,

Lotte Harper is online and recording. Be a part of the Lotte Harper family. Learn daily about software operations, database, security, frontend JavaScript, HTML and CSS along with JS APIs, WebSocket consumers, WebRTC, machine learning (ML), artificial intelligence (AI) and rendering engines, as well as Python server backend logic with requests, PyPI packages, OpenCV, **** recognition, barcode scanning, video and audio editing and sync, podcasting, universal translation, blogging,

Lotte Harper is online and recording. Be a part of the Lotte Harper family. Learn daily about software operations, database, security, frontend JavaScript, HTML and CSS along with JS APIs, WebSocket consumers, WebRTC, machine learning (ML), artificial intelligence (AI) and rendering engines, as well as Python server backend logic with requests, PyPI packages, OpenCV, **** recognition, barcode scanning, video and audio editing and sync, podcasting, universal translation, blogging,

Lotte Harper is online and recording. Be a part of the Lotte Harper family. Learn daily about software operations, database, security, frontend JavaScript, HTML and CSS along with JS APIs, WebSocket consumers, WebRTC, machine learning (ML), artificial intelligence (AI) and rendering engines, as well as Python server backend logic with requests, PyPI packages, OpenCV, **** recognition, barcode scanning, video and audio editing and sync, podcasting, universal translation, blogging,

Lotte Harper is online and recording. Be a part of the Lotte Harper family. Learn daily about software operations, database, security, frontend JavaScript, HTML and CSS along with JS APIs, WebSocket consumers, WebRTC, machine learning (ML), artificial intelligence (AI) and rendering engines, as well as Python server backend logic with requests, PyPI packages, OpenCV, **** recognition, barcode scanning, video and audio editing and sync, podcasting, universal translation, blogging,