FeedCity

Decoding Meshtastic with GNURadio on a Raspberry Pi Jeff Geerling July 31, 2025

Ollama's new app

Ollama has been one of my favorite ways to run local models for a while - it makes it really easy to download models, and it's smart about keeping them resident in memory while they are being used and then cleaning them out after they stop receiving traffic.

The one missing feature to date has been an interface: Ollama has been exclusively command-line, which is fine for the CLI literate among us and not much use for everyone else.

They've finally fixed that! The new app's interface is accessible from the existing system tray menu and lets you chat with any of your installed models. Vision models can accept images through the new interface as well.

Via Hacker News

Tags: ai, generative-ai, local-llms, llms, ollama

When you vibe code, you are incurring tech debt as fast as the LLM can spit it out. Which is why vibe coding is perfect for prototypes and throwaway projects: It's only legacy code if you have to maintain it! [...]

The worst possible situation is to have a non-programmer vibe code a large project that they intend to maintain. This would be the equivalent of giving a credit card to a child without first explaining the concept of debt. [...]

If you don't understand the code, your only recourse is to ask AI to fix it for you, which is like paying off credit card debt with another credit card.

— Steve Krouse, Vibe code is legacy code

Tags: vibe-coding, ai-assisted-programming, generative-ai, steve-krouse, ai, llms

Fraudsters are flooding Discord and other social media platforms with ads for hundreds of polished online gaming and wagering websites that lure people with free credits and eventually abscond with any cryptocurrency funds deposited by players. Here's a closer look at the social engineering tactics and remarkable traits of this sprawling network of more than 1,200 scam sites.

Today's links Delta's AI-based price-gouging: Running an airline like a hedge-fund. Hey look at this: Delights to delectate. Object permanence: DHS RFIDs tourists; Solar heroin; International development and the copyfight Upcoming appearances: Where to find me. Recent appeara...

Something that has become undeniable this month is that the best available open weight models now come from the Chinese AI labs. I continue to have a lot of love for Mistral, Gemma and Llama but my feeling is that Qwen, Moonshot and Z.ai have positively smoked them over the ...

Qwen3-30B-A3B-Thinking-2507 Yesterday was Qwen3-30B-A3B-Instruct-2507. Qwen are clearly committed to their new split between reasoning and non-reasoning models (a reversal from Qwen 3 in April), because today they released the new reasoning partner to yesterday's model: Qwen...

A taste of Lean.

OpenAI: Introducing study mode New ChatGPT feature, which can be triggered by typing /study or by visiting chatgpt.com/studymode. OpenAI say: Under the hood, study mode is powered by custom system instructions we’ve written in collaboration with teachers, scientists, and pe...

Qwen/Qwen3-30B-A3B-Instruct-2507 New model update from Qwen, improving on their previous Qwen3-30B-A3B release from late April. In their tweet they said: Smarter, faster, and local deployment-friendly. ✨ Key Enhancements: ✅ Enhanced reasoning, coding, and math skills ✅ Broa...

Today's links Boss-politics antitrust and the MAGA crackup: The Tunney Act stirs the pot. Hey look at this: Delights to delectate. Object permanence: Hearware, 10,000 superballs; Bitcoin is not socialist; Stupid and dangerous video game cheating lawsuit. Upcoming appearances:...

Our plan is to build direct traffic to our site. and newsletters just one kind of direct traffic in the end. I don’t intend to ever rely on someone else’s distribution ever again ;

— Nilay Patel, on The Verge's new newsletter strategy

Tags: nilay-patel, journalism, email

Recording vintage CRTs with a modern Sony mirrorless camera Jeff Geerling July 29, 2025

I wrote about the new GLM-4.5 model family yesterday - new open weight (MIT licensed) models from Z.ai in China which their benchmarks claim score highly in coding even against models such as Claude Sonnet 4. The models are pretty big - the smaller GLM-4.5 Air model is still...

With the primary backup strategies and methodologies introduced, we've reached the point where we can get specific: the Backup Server configuration. When choosing the type of backup server to use, I tend to favor specific setups: either I trust a professional backup service...

We’re rolling out new weekly rate limits for Claude Pro and Max in late August. We estimate they’ll apply to less than 5% of subscribers based on current usage. [...]

Some of the biggest Claude Code fans are running it continuously in the background, 24/7.

These uses are remarkable and we want to enable them. But a few outlying cases are very costly to support. For example, one user consumed tens of thousands in model usage on a $200 plan.

— Anthropic

Tags: anthropic, claude-code, llm-pricing, generative-ai, ai, llms

A beginner's guide to modding Celestia.

ChatGPT and Claude won’t, but Gemini will.

Today's links How twiddling enshittifies your brain: They preferentially mess with the stuff you rely on the most. Hey look at this: Delights to delectate. Object permanence: Used books economics; Adbusters sf; Branson vs virgins; Shark knife; Protesters must pledge souls to ...

GLM-4.5: Reasoning, Coding, and Agentic Abililties Another day, another significant new open weight model release from a Chinese frontier AI lab. This time it's Z.ai - who rebranded (at least in English) from Zhipu AI a few months ago. They just dropped GLM-4.5-Base, GLM-4.5...