Popular AI | Substack

Biased LLMs and the risk to student thinking

AI in education is not a simple cheating story. Biased LLMs can train students to outsource thought unless schools teach judgment.

Jun 28 • Ben Geudens

Best CPU-only local LLMs in 2026: what runs well without a GPU

Running local AI without a GPU? Here are the best CPU-only local LLMs, which sizes make sense, and when bigger models get painfully slow.

8 hrs ago • Popular AI

RTX 5090 vs RTX 4090 vs RTX 3090: which wins for local AI?

Choose the best GPU for local AI with this RTX 3090, RTX 4090, and RTX 5090 comparison for local LLMs, ComfyUI, and coding agents.

Jul 4 • Popular AI

Stronger AI cyber tools mean developers need faster fixes

AI cyber tools are shrinking the gap between discovery and exploitation. Here is how small teams should patch, verify, and reduce exposure.

Jul 3 • Popular AI

GLM-5.2 is the open coding model to test next

GLM-5.2 looks like a serious open coding model for agents, but hardware, quantization, vLLM, and SGLang decide how practical it is.

Jul 2 • Popular AI

Latest Articles

M4 Max or Ryzen AI Max+ 395 for local AI? What to buy

Choosing between M4 Max and Ryzen AI Max+ 395 for local AI? Compare memory, speed, software support, price, and real workload fit.

Jul 1 • Popular AI

AI super PAC sockpuppets: the fake doomer scandal, explained

The AI super PAC sockpuppet story reveals how pro-AI political money, fake personas, data centers and local AI reshape data center politics.

Jun 27 • Popular AI

Claude Code scams now use real claude.ai links. Stay safe

Attackers are using Claude shared chats and Google Ads to push fake Claude Code commands. Use this checklist before installing.

Jun 26 • Popular AI

GMKtec EVO-X3: should you buy this 128GB local AI mini PC?

A practical GMKtec EVO-X3 buying guide for local LLM users comparing 128GB unified memory against NVIDIA GPUs, Mac Studio, and DGX Spark.

Jun 25 • Popular AI

Popular AI

Subscribe for fixes, walkthroughs, and AI briefings.

AI news and analysis

PewDiePie built a private AI workspace, and it is worth watching

PewDiePie’s Odysseus AI workspace brings local models, agents, memory, files, research, and email into one self-hosted AI interface.

Jun 1 • Popular AI

Will the average user make AI worse for power users?

AI chatbots may keep getting smarter while their defaults grow safer, softer and more agreeable. Here’s why power users should care.

May 18 • Popular AI

Should you buy local AI hardware in 2026? The honest answer

Should you buy local AI hardware in 2026 or stick with ChatGPT, Claude, and Perplexity? Here is the practical buyer’s guide.

May 12 • Popular AI

ChatGPT 5.5 is a real upgrade, but not for everyone

GPT-5.5 looks like a serious upgrade for professional AI work. Here is what changed, what it costs and who should test it now.

Apr 28 • Popular AI

Claude Mythos shows Anthropic’s best AI is behind closed doors

Claude Mythos may be a leap in agentic coding and offensive cyber work. Anthropic’s gated rollout reveals how frontier AI power is really distributed.

Apr 13 • Popular AI

Explore Local AI

Best CPU-only local LLMs in 2026: what runs well without a GPU

Running local AI without a GPU? Here are the best CPU-only local LLMs, which sizes make sense, and when bigger models get painfully slow.

8 hrs ago • Popular AI

RTX 5090 vs RTX 4090 vs RTX 3090: which wins for local AI?

Choose the best GPU for local AI with this RTX 3090, RTX 4090, and RTX 5090 comparison for local LLMs, ComfyUI, and coding agents.

Jul 4 • Popular AI

GLM-5.2 is the open coding model to test next

GLM-5.2 looks like a serious open coding model for agents, but hardware, quantization, vLLM, and SGLang decide how practical it is.

Jul 2 • Popular AI

M4 Max or Ryzen AI Max+ 395 for local AI? What to buy

Choosing between M4 Max and Ryzen AI Max+ 395 for local AI? Compare memory, speed, software support, price, and real workload fit.

Jul 1 • Popular AI

AI super PAC sockpuppets: the fake doomer scandal, explained

The AI super PAC sockpuppet story reveals how pro-AI political money, fake personas, data centers and local AI reshape data center politics.

Jun 27 • Popular AI

AI fixes, guides and walkthroughs

ComfyUI extra_model_paths.yaml not working? Here’s the fix

ComfyUI not finding checkpoints, LoRAs, VAEs, or upscalers? Here’s how to repair extra_model_paths.yaml and confirm it works.

Jun 8 • Popular AI

How to fix ComfyUI Desktop “unrecognized arguments: --normalvram” crashes

ComfyUI Desktop crashing with “unrecognized arguments: --normalvram”? Learn how to remove bad launch flags, update safely, check logs, and run ComfyUI…

Jun 6 • Popular AI

How to run Gemma 4 31B locally with Ollama for private writing

Gemma 4 31B can handle long-context writing locally, but memory matters. Here is how to set it up without chasing 256K too soon.

Jun 5 • Popular AI

The ChatGPT sidebar sucks now. Here’s how to fix it.

If your ChatGPT pinned chats, GPTs, or Projects disappeared, do not panic. Here is what changed and how to get them back.

Jun 3 • Ben Geudens

A local Perplexity alternative with Vane, Ollama and SearXNG

Build a Perplexity-style research stack you control using Vane, Ollama, Docker, and SearXNG for private web search.

Jun 2 • Popular AI

Llama-3-Groq-70B-Tool-Use: scale private agents locally in Ollama

A practical guide to scaling local AI agent workflows with Ollama, tool schemas, permission controls, monitoring, and private knowledge search.

Jun 2 • Popular AI

Popular AI

Popular AI

Practical AI for people who want capability without permission: local setups, troubleshooting, tool comparisons, and clear-eyed AI analysis.

Top posts

The Best Mac mini for local LLMs in 2026: M4 vs M4 Pro for Ollama and MLX

Mar 25 • Popular AI

Prohibited AI practices for thee…

Jul 22, 2025 • Ben Geudens

ChatGPT’s ‘piss filter’: why AI images skew yellow (and how to fix it)

Mar 2 • Popular AI

Mac mini LLM performance in 2026: which model should you buy?

May 12 • Popular AI

The best CPU for running local LLMs: top AMD vs Intel processors ranked

Mar 26 • Popular AI

AI builds, hardware and buyer's guides

RTX 5090 vs RTX 4090 vs RTX 3090: which wins for local AI?

Choose the best GPU for local AI with this RTX 3090, RTX 4090, and RTX 5090 comparison for local LLMs, ComfyUI, and coding agents.

Jul 4 • Popular AI

M4 Max or Ryzen AI Max+ 395 for local AI? What to buy

Choosing between M4 Max and Ryzen AI Max+ 395 for local AI? Compare memory, speed, software support, price, and real workload fit.

Jul 1 • Popular AI

GMKtec EVO-X3: should you buy this 128GB local AI mini PC?

A practical GMKtec EVO-X3 buying guide for local LLM users comparing 128GB unified memory against NVIDIA GPUs, Mac Studio, and DGX Spark.

Jun 25 • Popular AI

Is a Strix Halo mini PC worth buying for local AI?

A Ryzen AI Max+ 395 mini PC looks perfect for local AI, but speed, software support, and pricing decide whether it is worth buying.

Jun 24 • Popular AI

The RTX 5090 for local AI: fast bandwidth, same VRAM wall

For local AI, the RTX 5090 shines with 8B to 32B models. Bigger 70B workloads still point to RTX PRO 6000, H100, or cloud GPUs.

Jun 19 • Popular AI

Are dual RTX 3090s still worth buying for local AI in 2026?

Thinking about swapping an RTX 4080 for dual RTX 3090s? Here is when 48GB VRAM matters for local AI, and when it is not worth it.

Jun 15 • Popular AI

Recommendations

Popular Philosophy

Popular Philosophy

Follow Popular AI

The latest from

Popular AI

Best CPU-only local LLMs in 2026: what runs well without a GPU

Ben Geudens

Biased LLMs and the risk to student thinking

AI and information freedom

Biased LLMs and the risk to student thinking

AI in education is not a simple cheating story. Biased LLMs can train students to outsource thought unless schools teach judgment.

Jun 28 • Ben Geudens

Should you buy local AI hardware in 2026? The honest answer

Should you buy local AI hardware in 2026 or stick with ChatGPT, Claude, and Perplexity? Here is the practical buyer’s guide.

May 12 • Popular AI

6:30

The rise of culture-on-demand: reclaiming media from the intellectual property hogs

Open source generative AI is turning culture into something users can generate on demand, putting Hollywood, copyright, and IP business models under new…

Apr 1 • Popular AI and Ben Geudens

The worst people to “make AI safe”

Why allowing history’s most lethal gangs to regulate superintelligences is a recipe for disaster and why governments, and their moronic sycophants…

Feb 16 • Ben Geudens

Subscribe

Practical AI for people who want capability without permission: local setups, troubleshooting, tool comparisons, and clear-eyed AI analysis.

About Archive Recommendations Sitemap

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts