A $20k American-made electric pickup with no paint, no stereo, no screen

FBI arrests judge accused of helping man evade immigration authorities

Writing "/etc/hosts" breaks the Substack editor

DeepMind releases Lyria 2 music generation model

Lossless LLM compression for efficient GPU inference via dynamic-length float

Wikipedia’s nonprofit status questioned by D.C. U.S. attorney

Eurorack Knob Idea

The Policy Puppetry Prompt: Novel bypass for major LLMs

Avoiding skill atrophy in the age of AI

What If We Could Rebuild Kafka from Scratch?

GCC 15.1

Reproducibility project fails to validate dozens of biomedical studies

Hegseth had an unsecured internet line set up in his office to connect to Signal

Hey HN, Anders and Tom here - we’ve been building an end-to-end testing framework powered by visual LLM agents to replace traditional web testing.We know there&#x27;s a lot of noise about different browser agents. If you&#x27;ve tried any of them, you know they&#x27;re slow, expensive, and inconsistent. That&#x27;s why we built an agent specifically for running test cases and optimized it just for that:- Pure vision instead of error prone &quot;set-of-marks&quot; system (the colorful boxes you see in browser-use for example)- Use tiny VLM (Moondream) instead of OpenAI&#x2F;Anthropic computer use for dramatically faster and cheaper execution- Use two agents: one for planning and adapting test cases and one for executing them quickly and consistently.The idea is the planner builds up a general plan which the executor runs. We can save this plan and re-run it with only the executor for quick, cheap, and consistent runs. When something goes wrong, it can kick back out to the planner agent and re-adjust the test.It’s completely open source. Would love to have more people try it out and tell us how we can make it great.Repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;magnitudedev&#x2F;magnitude">https:&#x2F;&#x2F;github.com&#x2F;magnitudedev&#x2F;magnitude</a>

Show HN: Magnitude – open-source, AI-native test framework for web apps

I&#x27;ve had an idea for a long time to generate a cute coloring book based on family photos, send it to a printing service, and then deliver it to people.Last month, when OpenAI&#x27;s Sora was released for public use I (foolishly) thought I&#x27;d manually drag-and-drop each order’s photos into Sora&#x27;s UI and copy the resulting images back into my system. This took way too much time (about an hour for each of the few books I made and tested with family and friends). It clearly wasn&#x27;t possible to release this version because I’d be losing a huge amount of time on every order. So instead, I decided I&#x27;d finish off the project as best I could, put it &quot;on ice,&quot; and wait for the API release.The API is now released (quicker than I thought it&#x27;d be, too!) and I integrated it last night. I&#x27;d love your feedback on any and all aspects.The market is mostly family-based, but from my testing of the physical book I&#x27;ve found that both adults and kids enjoy coloring them in (it&#x27;s surprisingly cathartic and creative). If you would like to order one you can get 10% off by tapping the total price line item five times.

Show HN: I used OpenAI's new image API for a personalized coloring book service