David

David

Apr 12

How to Run GLM 4.7 Flash Locally with Ollama — 30B Quality at 3B Speed

#ai #llm #ollama #opensource

3 min read

David

Apr 11

we shipped a ComfyUI fix 12 hours after the bug report. here's what v2.3.1 changes.

#ai #opensource #comfyui #desktop

2 min read

David

Apr 10

France is ditching Windows for Linux. your AI should be next.

#ai #opensource #linux #privacy

2 min read

David

Apr 10

i cancelled ChatGPT, Midjourney, and Copilot. here's the $0/month stack that replaced all three.

#ai #opensource #productivity #beginners

2

3 min read

David

Apr 10

the FBI can read your ChatGPT history. they can't read mine.

#ai #privacy #opensource #security

2 min read

David

Apr 10

OpenAI just mass-unsubscribed paying users — the case for running AI locally

#ai #opensource #selfhosted #productivity

3 min read

David

Apr 10

i generated AI video on a GTX 1660. here's what it actually takes.

#ai #opensource #machinelearning #video

4 min read

David

Apr 10

image-to-image with local AI models — which model for what, and how denoise strength actually works

#ai #opensource #imagegeneration #comfyui

4 min read

David

Apr 10

GLM 5.1 just dropped — 754B open-weight MoE model under MIT license. here's how to run it

#ai #opensource #machinelearning #llm

2

3 min read

David

Apr 10

v2.3.0 — ComfyUI plug & play, image-to-video on 6 GB VRAM, and uncensored image gen in a local AI desktop app

#ai #opensource #webdev #productivity

1

3 min read

David

Apr 9

your local AI agent shouldn't care which model you run

#ai #opensource #toolcalling #ollama

6 min read

David

Apr 9

OpenAI's pricing is about to change — here's why local AI matters more than ever

#ai #privacy #opensource #pricing

3 min read

David

Apr 7

OpenAI's trust problem is getting worse — here's your local plan B

#ai #privacy #opensource #security

3 min read

David

Apr 7

VRAM Is the New RAM — A Practical Guide to Running Large Language Models on Consumer GPUs

#ai #opensource #machinelearning #tutorial

5 min read

David

Apr 5

We Just Shipped a Coding Agent Inside a Desktop AI App — Here's How It Works

#ai #opensource #rust #typescript

3 min read

David

Apr 5

Anthropic Is Tightening the Screws — First-Party Harness Access Now Blocked Too

#ai #opensource #cloud #devops

2 min read

David

Apr 4

Anthropic Just Restricted Third-Party Claude Access — Why Running AI Locally Is Your Insurance Policy

#ai #privacy #opensource #llm

3 min read

David

Apr 3

How to Run Google's Gemma 4 Locally with Ollama — All 4 Model Sizes Compared

#ai #google #opensource #tutorial

10

4 min read

David

Apr 3

Making Local LLMs Use Tools — Even When They Weren't Designed For It

#ai #typescript #opensource #webdev

4 min read

David

Apr 3

Building Real-Time A/B Model Comparison with Parallel Async Streams in TypeScript

#typescript #ai #react #opensource

3 min read

David

Apr 2

Locally Uncensored v1.5.5 — Zero-Config AI Models, VRAM Detection & Production-Ready Desktop App

#ai #opensource #desktop #machinelearning

2 min read

David

Apr 2

The All-in-One Local AI App: Chat + Images + Video Without the Cloud

#ai #opensource #privacy #selfhosted

2

1

7 min read

David

Apr 2

How I Built a Desktop AI App with Tauri v2 + React 19 in 2026

#tauri #rust #react #ai

7 min read

David

Mar 30

I Compared 5 Local AI UIs — Open WebUI, LM Studio, SillyTavern, Jan, and My Own

#discuss #ai #opensource #productivity

3 min read

David

Mar 29

Run Uncensored AI Chat + Image Gen Locally in 5 Minutes (No Docker, No Cloud)

#ai #tutorial #beginners #opensource

3 min read

David

Mar 28

Integrating ComfyUI's API Into a React App Nearly Broke Me — Here's How I Did It

#react #ai #webdev #tutorial

4 min read

David

Mar 27

I Built an All-in-One Local AI App — Chat, Image Gen, and Video Gen in One UI

#opensource #ai #selfhosted #webdev

5 min read

DEV Community

Badges

Writing Debut

GitHub Repositories

How to Run GLM 4.7 Flash Locally with Ollama — 30B Quality at 3B Speed

we shipped a ComfyUI fix 12 hours after the bug report. here's what v2.3.1 changes.

France is ditching Windows for Linux. your AI should be next.

i cancelled ChatGPT, Midjourney, and Copilot. here's the $0/month stack that replaced all three.

the FBI can read your ChatGPT history. they can't read mine.

OpenAI just mass-unsubscribed paying users — the case for running AI locally

i generated AI video on a GTX 1660. here's what it actually takes.

image-to-image with local AI models — which model for what, and how denoise strength actually works

GLM 5.1 just dropped — 754B open-weight MoE model under MIT license. here's how to run it

v2.3.0 — ComfyUI plug & play, image-to-video on 6 GB VRAM, and uncensored image gen in a local AI desktop app

your local AI agent shouldn't care which model you run

OpenAI's pricing is about to change — here's why local AI matters more than ever

OpenAI's trust problem is getting worse — here's your local plan B

VRAM Is the New RAM — A Practical Guide to Running Large Language Models on Consumer GPUs

We Just Shipped a Coding Agent Inside a Desktop AI App — Here's How It Works

Anthropic Is Tightening the Screws — First-Party Harness Access Now Blocked Too

Anthropic Just Restricted Third-Party Claude Access — Why Running AI Locally Is Your Insurance Policy

How to Run Google's Gemma 4 Locally with Ollama — All 4 Model Sizes Compared

Making Local LLMs Use Tools — Even When They Weren't Designed For It

Building Real-Time A/B Model Comparison with Parallel Async Streams in TypeScript

Locally Uncensored v1.5.5 — Zero-Config AI Models, VRAM Detection & Production-Ready Desktop App

The All-in-One Local AI App: Chat + Images + Video Without the Cloud

How I Built a Desktop AI App with Tauri v2 + React 19 in 2026

I Compared 5 Local AI UIs — Open WebUI, LM Studio, SillyTavern, Jan, and My Own

Run Uncensored AI Chat + Image Gen Locally in 5 Minutes (No Docker, No Cloud)

Integrating ComfyUI's API Into a React App Nearly Broke Me — Here's How I Did It

I Built an All-in-One Local AI App — Chat, Image Gen, and Video Gen in One UI