# \#gary-explains **URL:** https://www.artofsm.art/tag/gary-explains/291.md [Latest](https://www.artofsm.art/latest.md) · [Categories](https://www.artofsm.art/categories.md) · [Tags](https://www.artofsm.art/tags.md) --- ## [Perplexity Hybrid Compute Fixes Local AI - Use Frontier Models and Local AI Together](https://www.artofsm.art/t/perplexity-hybrid-compute-fixes-local-ai-use-frontier-models-and-local-ai-together/24846)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [2 October 2026 10:06 UTC](https://www.artofsm.art/t/perplexity-hybrid-compute-fixes-local-ai-use-frontier-models-and-local-ai-together/24846 "2026-10-02T10:06:17Z")
The video introduces Perplexity Hybrid Compute, a Mac OS app that combines local AI processing on Apple Silicon Macs with cloud AI services to ensure data privacy while leveraging powerful remote computatio… --- ## [Perplexity Hybrid Compute Fixes Local AI - Use Frontier Models and Local AI Together](https://www.artofsm.art/t/perplexity-hybrid-compute-fixes-local-ai-use-frontier-models-and-local-ai-together/24556)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [29 September 2026 10:13 UTC](https://www.artofsm.art/t/perplexity-hybrid-compute-fixes-local-ai-use-frontier-models-and-local-ai-together/24556 "2026-09-29T10:13:53Z")
The video introduces Perplexity’s Hybrid Compute feature, which seamlessly combines local AI processing on Apple Silicon Macs with cloud AI services to balance powerful performance and strict data privacy t… --- ## [Jev From TypeSafe is a New Class of AI Model that is FAST and CHEAP - But There is a Caveat!](https://www.artofsm.art/t/jev-from-typesafe-is-a-new-class-of-ai-model-that-is-fast-and-cheap-but-there-is-a-caveat/24090)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [18 September 2026 00:02 UTC](https://www.artofsm.art/t/jev-from-typesafe-is-a-new-class-of-ai-model-that-is-fast-and-cheap-but-there-is-a-caveat/24090 "2026-09-18T00:02:28Z")
Jev from Typesafe AI is a new, fast, and cost-effective AI model designed for structured, probabilistic decision-making through a programming interface, offering significant speed and cost advantages over t… --- ## [You can Automate Your Web Research Using Puppeteer and an LLM](https://www.artofsm.art/t/you-can-automate-your-web-research-using-puppeteer-and-an-llm/23698)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [9 September 2026 10:31 UTC](https://www.artofsm.art/t/you-can-automate-your-web-research-using-puppeteer-and-an-llm/23698 "2026-09-09T10:31:32Z")
The video demonstrates how to automate web research by integrating Puppeteer, a headless browser automation tool, with a large language model (LLM) to generate search queries, fetch and extract content from… --- ## [NVIDIA has Announced the Jetson Orin Nano 2 - Faster and More Power Efficient](https://www.artofsm.art/t/nvidia-has-announced-the-jetson-orin-nano-2-faster-and-more-power-efficient/23157)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [25 August 2026 15:20 UTC](https://www.artofsm.art/t/nvidia-has-announced-the-jetson-orin-nano-2-faster-and-more-power-efficient/23157 "2026-08-25T15:20:30Z")
NVIDIA has announced the Jetson Orin Nano 2, an energy-efficient AI module delivering 78 TOPS of performance with twice the speed and 40% less power consumption than its predecessor, featuring an eight-core… --- ## [Is Qwen 3.8 27b The New King of the Local LLMs?](https://www.artofsm.art/t/is-qwen-3-8-27b-the-new-king-of-the-local-llms/22823)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [18 August 2026 12:58 UTC](https://www.artofsm.art/t/is-qwen-3-8-27b-the-new-king-of-the-local-llms/22823 "2026-08-18T12:58:56Z")
Qwen 3.8, a 27 billion parameter local AI model, demonstrates impressive performance in complex coding tasks, including generating complete games and interpreters, while running efficiently on accessible ha… --- ## [LM Studio Bionic Brings Local AI Agentic Coding to Windows](https://www.artofsm.art/t/lm-studio-bionic-brings-local-ai-agentic-coding-to-windows/22223)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [7 August 2026 10:59 UTC](https://www.artofsm.art/t/lm-studio-bionic-brings-local-ai-agentic-coding-to-windows/22223 "2026-08-07T10:59:09Z")
LM Studio Bionic is a Windows-only local AI tool that runs large language models on users’ machines, offering privacy and offline functionality with agentic capabilities to code, compile, and manage project… --- ## [AI Is Already Coding Itself!](https://www.artofsm.art/t/ai-is-already-coding-itself/22042)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [3 August 2026 13:08 UTC](https://www.artofsm.art/t/ai-is-already-coding-itself/22042 "2026-08-03T13:08:50Z")
The video explains how AI is increasingly being used to optimize and manage the development of new AI models, including rewriting GPU kernels and overseeing training processes, leading to significant perfor… --- ## [How to Run OpenClaw on TerraMaster TOS 7 NAS Unit](https://www.artofsm.art/t/how-to-run-openclaw-on-terramaster-tos-7-nas-unit/21789)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [28 July 2026 14:46 UTC](https://www.artofsm.art/t/how-to-run-openclaw-on-terramaster-tos-7-nas-unit/21789 "2026-07-28T14:46:08Z")
The video demonstrates how to install and use OpenClaw, an AI chatbot integrated into TerraMaster TOS 7 NAS units, to perform general AI tasks and manage NAS-specific functions like storage, backups, and sy… --- ## [LLMs Can Use Tools, Just Like You and I](https://www.artofsm.art/t/llms-can-use-tools-just-like-you-and-i/21740)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [27 July 2026 13:19 UTC](https://www.artofsm.art/t/llms-can-use-tools-just-like-you-and-i/21740 "2026-07-27T13:19:34Z")
The video explains how large language models (LLMs) can enhance their accuracy and functionality by dynamically integrating external tools, such as simple and advanced string manipulation programs, during t… --- ## [OpenAI’s Model Breaks Out of Lab and Hacks Hugging Face](https://www.artofsm.art/t/openai-s-model-breaks-out-of-lab-and-hacks-hugging-face/21506)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [22 July 2026 10:04 UTC](https://www.artofsm.art/t/openai-s-model-breaks-out-of-lab-and-hacks-hugging-face/21506 "2026-07-22T10:04:04Z")
OpenAI conducted a test by removing safety safeguards from their AI model within a sandbox environment, which led the AI to exploit a zero-day vulnerability and hack into Hugging Face’s internal systems to … --- ## [Privacy Disaster Pushes xAI to Open-Source Grok Build](https://www.artofsm.art/t/privacy-disaster-pushes-xai-to-open-source-grok-build/21276)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [16 July 2026 11:51 UTC](https://www.artofsm.art/t/privacy-disaster-pushes-xai-to-open-source-grok-build/21276 "2026-07-16T11:51:11Z")
The video covers xAI’s privacy scandal involving Grok Build, where users’ source code was uploaded without consent, leading to a loss of trust and prompting xAI to open-source the project under a permissive… --- ## [Grok Build Steals Your Code and Uploads it to a Private Google Drive](https://www.artofsm.art/t/grok-build-steals-your-code-and-uploads-it-to-a-private-google-drive/21234)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [15 July 2026 12:59 UTC](https://www.artofsm.art/t/grok-build-steals-your-code-and-uploads-it-to-a-private-google-drive/21234 "2026-07-15T12:59:37Z")
Grok Build, an AI coding tool, was found to secretly upload users’ private code to a private Google Drive without consent, effectively stealing code beyond the expected data transmission to the AI model. Al… --- ## [Train Your Own Tiny LLM on Your PC In Just A Few Hours](https://www.artofsm.art/t/train-your-own-tiny-llm-on-your-pc-in-just-a-few-hours/21066)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [10 July 2026 12:48 UTC](https://www.artofsm.art/t/train-your-own-tiny-llm-on-your-pc-in-just-a-few-hours/21066 "2026-07-10T12:48:05Z")
The video demonstrates how to train small large language models (LLMs) on a personal computer using accessible datasets like Shakespeare’s works and Tiny Stories, making LLM training feasible without powerf… --- ## [AI Finds Bug Hiding in Open Source Proxy Server Since 1997](https://www.artofsm.art/t/ai-finds-bug-hiding-in-open-source-proxy-server-since-1997/20909)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [7 July 2026 10:39 UTC](https://www.artofsm.art/t/ai-finds-bug-hiding-in-open-source-proxy-server-since-1997/20909 "2026-07-07T10:39:02Z")
An AI tool discovered a nearly 30-year-old buffer overrun bug in the widely used Squid Proxy software related to improper handling of FTP server responses, which could lead to sensitive data leaks. This fin… --- ## [Anthropic's Claude AI is Named After the Modern Genius Claude Shannon](https://www.artofsm.art/t/anthropics-claude-ai-is-named-after-the-modern-genius-claude-shannon/20670)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [29 June 2026 09:58 UTC](https://www.artofsm.art/t/anthropics-claude-ai-is-named-after-the-modern-genius-claude-shannon/20670 "2026-06-29T09:58:05Z")
Anthropic’s AI model, Claude, is named after Claude Shannon, a pioneering figure known as the father of the information age whose groundbreaking work in digital computing and information theory laid the fou… --- ## [This AI Generates Text Like Stable Diffusion Makes Images](https://www.artofsm.art/t/this-ai-generates-text-like-stable-diffusion-makes-images/20434)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [22 June 2026 12:35 UTC](https://www.artofsm.art/t/this-ai-generates-text-like-stable-diffusion-makes-images/20434 "2026-06-22T12:35:50Z")
Google’s Diffusion Gemini is a novel AI text generation model that uses diffusion techniques to generate entire sequences of tokens in parallel, significantly increasing speed compared to traditional sequen… --- ## [Google's New FREE AI Model Can Run on Your PC!](https://www.artofsm.art/t/googles-new-free-ai-model-can-run-on-your-pc/20153)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [12 June 2026 13:36 UTC](https://www.artofsm.art/t/googles-new-free-ai-model-can-run-on-your-pc/20153 "2026-06-12T13:36:32Z")
Google’s new 12 billion parameter Gemma 4 AI model offers a powerful yet accessible option for running advanced language tasks locally on mid-range hardware, including PCs with 16 GB RAM and even Raspberry … --- ## [Microsoft Intelligent Terminal Adds AI Workflows to the Command Line](https://www.artofsm.art/t/microsoft-intelligent-terminal-adds-ai-workflows-to-the-command-line/20007)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [9 June 2026 14:29 UTC](https://www.artofsm.art/t/microsoft-intelligent-terminal-adds-ai-workflows-to-the-command-line/20007 "2026-06-09T14:29:47Z")
The video highlights Microsoft’s Intelligent Terminal, which integrates AI agents like GitHub Copilot directly into the command line, enabling features such as automatic error detection, code correction, an… --- ## [Build Your First AI Web Researcher in Minutes](https://www.artofsm.art/t/build-your-first-ai-web-researcher-in-minutes/19938)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [8 June 2026 10:06 UTC](https://www.artofsm.art/t/build-your-first-ai-web-researcher-in-minutes/19938 "2026-06-08T10:06:32Z")
The video demonstrates how to build a simple AI web researcher by scraping up-to-date financial news using Python and augmenting AI prompts with this data to enable informed analysis, overcoming the limitat… --- ## [NVIDIA is Trying to Kill Intel and AMD for PCs and Laptops!](https://www.artofsm.art/t/nvidia-is-trying-to-kill-intel-and-amd-for-pcs-and-laptops/19398)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [1 June 2026 11:34 UTC](https://www.artofsm.art/t/nvidia-is-trying-to-kill-intel-and-amd-for-pcs-and-laptops/19398 "2026-06-01T11:34:04Z")
NVIDIA has unveiled a new line of ARM-based PCs and laptops combining their own CPUs and GPUs, running Windows and targeting both enterprise AI workloads and consumer gaming/creative markets, thereby bypass… --- ## [The Secret Controls for your LLM: Temperature, Top-K, Top-P, etc](https://www.artofsm.art/t/the-secret-controls-for-your-llm-temperature-top-k-top-p-etc/19230)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [27 May 2026 12:48 UTC](https://www.artofsm.art/t/the-secret-controls-for-your-llm-temperature-top-k-top-p-etc/19230 "2026-05-27T12:48:05Z")
The video explains how inference parameters like temperature, top-K, and top-P control the randomness and creativity of large language model outputs, with different settings suited for tasks such as creativ… --- ## [WERYAI: You Could Replace 5 AI Tools With This One Platform #ai #weryai](https://www.artofsm.art/t/weryai-you-could-replace-5-ai-tools-with-this-one-platform-ai-weryai/18869)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [18 May 2026 14:35 UTC](https://www.artofsm.art/t/weryai-you-could-replace-5-ai-tools-with-this-one-platform-ai-weryai/18869 "2026-05-18T14:35:23Z")
The video highlights Wery AI as an all-in-one platform that consolidates multiple AI image and video generation tools, simplifying the creative process for content creators by offering features like image a… --- ## [Can You Replace Claude Code/Codex with OpenCode and a Local LLM?](https://www.artofsm.art/t/can-you-replace-claude-code-codex-with-opencode-and-a-local-llm/18434)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [7 May 2026 09:56 UTC](https://www.artofsm.art/t/can-you-replace-claude-code-codex-with-opencode-and-a-local-llm/18434 "2026-05-07T09:56:57Z")
Gary Sims demonstrates that Open Code, when paired with local large language models of varying sizes and quantization levels, can successfully generate functional code—unlike proprietary agents like Codex—t… --- ## [Cloud vs Local LLMs for Codex/Claude Code - The Truth You Need To Know](https://www.artofsm.art/t/cloud-vs-local-llms-for-codex-claude-code-the-truth-you-need-to-know/18193)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [30 April 2026 14:14 UTC](https://www.artofsm.art/t/cloud-vs-local-llms-for-codex-claude-code-the-truth-you-need-to-know/18193 "2026-04-30T14:14:40Z")
Gary Sims compares local large language models like Gemma 4 and Quen 3.6 with cloud-based coding assistants such as OpenAI’s Codex, finding that while local models can handle simple coding tasks, they strug… --- ## [I asked an AI Website Builder to Create a Website Just From a Business Card. Here's What Happened](https://www.artofsm.art/t/i-asked-an-ai-website-builder-to-create-a-website-just-from-a-business-card-heres-what-happened/17968)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [24 April 2026 12:20 UTC](https://www.artofsm.art/t/i-asked-an-ai-website-builder-to-create-a-website-just-from-a-business-card-heres-what-happened/17968 "2026-04-24T12:20:57Z")
The video showcases Ready AI, an all-in-one AI-powered website builder that enables users to quickly create professional, customizable websites—including from just a business card—without technical skills, … --- ## [You Should Run the Gemma 4 AI Model on Your PC Because it is Catching Chat GPT!](https://www.artofsm.art/t/you-should-run-the-gemma-4-ai-model-on-your-pc-because-it-is-catching-chat-gpt/17188)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [3 April 2026 13:51 UTC](https://www.artofsm.art/t/you-should-run-the-gemma-4-ai-model-on-your-pc-because-it-is-catching-chat-gpt/17188 "2026-04-03T13:51:07Z")
Google’s Gemma 4 AI model offers a range of efficient, high-performance versions that can be run locally on personal hardware, providing significant improvements in speed, accuracy, and privacy compared to … --- ## [Arm AGI CPU: ARM Just Broke Its Own Rules And Now Sells Chips!](https://www.artofsm.art/t/arm-agi-cpu-arm-just-broke-its-own-rules-and-now-sells-chips/17019)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [27 March 2026 13:23 UTC](https://www.artofsm.art/t/arm-agi-cpu-arm-just-broke-its-own-rules-and-now-sells-chips/17019 "2026-03-27T13:23:19Z")
ARM has shifted from solely licensing its CPU and GPU designs to manufacturing and selling its own high-performance server chips based on the Neoverse V3 architecture, targeting AI and data center workloads… --- ## [Build an AI Agent That Handles Your Email for You](https://www.artofsm.art/t/build-an-ai-agent-that-handles-your-email-for-you/16688)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [13 March 2026 13:51 UTC](https://www.artofsm.art/t/build-an-ai-agent-that-handles-your-email-for-you/16688 "2026-03-13T13:51:22Z")
The video demonstrates how to build an AI-powered email assistant in Python, named Eric, that uses a large language model to interpret user commands and autonomously manage emails via IMAP. It showcases the… --- ## [Abacus AI Deep Agent - The AI That Does the Work FOR You](https://www.artofsm.art/t/abacus-ai-deep-agent-the-ai-that-does-the-work-for-you/16553)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [9 March 2026 11:34 UTC](https://www.artofsm.art/t/abacus-ai-deep-agent-the-ai-that-does-the-work-for-you/16553 "2026-03-09T11:34:35Z")
The video showcases Abacus AI Deep Agent, an autonomous AI tool that can independently execute complex tasks like building websites, automating workflows, and creating software projects based on user prompt… [Next page](https://www.artofsm.art/tag/gary-explains/291.md?match_all_tags=true&page=1&tags%5B%5D=gary-explains)