Writing by hand is good for your brain

<a href="https:&#x2F;&#x2F;littletech.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;littletech.org&#x2F;</a><a href="https:&#x2F;&#x2F;static.politico.com&#x2F;4a&#x2F;bf&#x2F;9c4021d8404386b0a311dcccf0e5&#x2F;lta-open-weight-ai-letter-7-22-26.pdf" rel="nofollow">https:&#x2F;&#x2F;static.politico.com&#x2F;4a&#x2F;bf&#x2F;9c4021d8404386b0a311dcccf0...</a>

Startup founders urge U.S. government not to shut off Chinese open weight AI

OpenAI and Hugging Face address security incident during model evaluation - <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=48997548">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=48997548</a> - July 2026 (1121 comments)

OpenAI’s accidental attack against Hugging Face is science fiction that happened

98.css

The Beam Engine

I’ve been building Echo (<a href="https:&#x2F;&#x2F;echo.tracerml.ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;echo.tracerml.ai&#x2F;</a>), an experiment in making one AI system out of a pool of open-weight models rather than choosing a single model and using it for every task.It started with a simple experiment. I took a group of models, including GLM-5.2, Kimi K2.7 and others, and ran them on the same evaluations. Then I measured what would happen if, for each problem, you somehow knew in advance which models would be useful and how their outputs should be combined.That hypothetical system performed substantially better than any individual model in the pool. Of course, it is not something you can actually deploy because it relies on knowing which decisions were good after seeing the result. Echo is my attempt to recover some of that advantage without having that information in advance.For each request, Echo decides how much computation to allocate, which models should participate, and how their work should be combined. Some prompts may only need a relatively small amount of inference, while others benefit from multiple models working on different parts of the problem.One thing that surprised me while building it was how complementary the models are. A model that is clearly weaker overall can still be extremely useful on particular problems or as part of a combination.On my first evaluation mix, Echo consistently performed better than the best individual model in its pool. It also reached roughly the same aggregate result as Fable, which I used as one of the stronger comparison systems, at around one third of the inference cost.There are still some cases where Echo makes the wrong allocation or combination decision. I’m currently spending a lot of time understanding those failures, as well as testing whether the same approach holds up on coding and agentic tasks where measuring the quality of each decision becomes much harder.I built a chat interface (echo.tracerml.ai) and an OpenAI-compatible API (<a href="https:&#x2F;&#x2F;echo.tracerml.ai&#x2F;docs&#x2F;api" rel="nofollow">https:&#x2F;&#x2F;echo.tracerml.ai&#x2F;docs&#x2F;api</a>) so the system can be tested outside the evaluation setup.Here is a short&#x2F;high level video on how it works: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=lJFJSvOdXhg" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=lJFJSvOdXhg</a>I wrote up the evaluation methodology, individual model results, costs and current limitations here: <a href="https:&#x2F;&#x2F;echo.tracerml.ai&#x2F;eval" rel="nofollow">https:&#x2F;&#x2F;echo.tracerml.ai&#x2F;eval</a>I would love for you to try it! Especially if you hit any weird failure cases or places where the allocation looks unintuitive.

Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

What happened to TheNumbers.com

Why Software Factories Fail (or: harness engineering is not enough)

I regret migrating to Codeberg

Flux 3

Software rendering in 500 lines of bare C++

DARPA, U.S. Air Force fly AI-controlled F-16

Learn OpenGL, extensive tutorial resource for learning Modern OpenGL

Fields Medals 2026

Building on ATProto

Hi HN, we are Marcos and Harrison, cofounders of Palmier (<a href="https:&#x2F;&#x2F;palmier.io">https:&#x2F;&#x2F;palmier.io</a>). We are building Palmier Pro, an open source macOS video editor, with built-in AI generation and a local MCP server that connects to your agent. Here are a few demos:- Making some AI transitions: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=hbM_-eR1GX4" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=hbM_-eR1GX4</a>- Multicam editing with Codex: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=SjS2q2LT1q8" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=SjS2q2LT1q8</a>- Cutting long form clips into shorts: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=PR66eN2ouuQ" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=PR66eN2ouuQ</a>We built Palmier Pro as an internal tool when we were making AI launch videos for other startups. The main problem it solved in the beginning was the back-and-forth between AI generation platform and video editor. The iteration loop was awkward: AI videos → download → import to editor → edit → realize we need to change the AI video → repeat. So we built a minimal video editor where we could let Claude generate AI videos inside the editor.As we gave more and more tools to the agent, we wanted to push to see what else agents can do in the video editing space. So today, your Claude&#x2F;Codex can:- Manage projects inside Palmier Pro- Import media from a public URL or filesystem to the project, and organize them in folders- Search media (by embedding footages using SigLIP2 running locally)- Edit the timeline (tracks&#x2F;clips&#x2F;keyframes operations)- Generate images, videos, sound effects, captions, music- Export videosThere are two ways for LLMs to interact with the editor: by connecting to the local MCP server, or using the in-app chat. Both use the same tools and APIs exposed by the video editor.We have seen people using MCP server to connect to their own workflow to automate massive-scale video editing (e.g. given this same podcast style, replicate it with other footages that I have). We have also seen people using the in-app chat where it lives closer to the editor UI, with lower latency for faster iteration.We don&#x27;t believe that AI is going to replace human creativity (nor should it), but where it can really help is in automating the gruntwork in video editing. Most work in the editing workflow is more mechanical than creative. Our vision is to build a video editor where AI can enable more individuals to create.Throughout our experiments, AI is not very good at creative editing, but given a pattern (transcription-based, beat-based), it can do a decent job at rough cut.We built Palmier Pro in Swift as an MVP because we wanted better performance and minimal dependencies (no nodejs&#x2F;webview), with some native macOS APIs like SpeechAnalyzer and CoreML for us to run some models locally. We use SpeechAnalyzer for local transcriber, SigLip2 to embed video frames, beat_this for beat detection, Silero VAD for silence detection, all running locally. The tradeoff is that we don&#x27;t support Linux or Windows at the moment.Palmier Pro is open source and free to try out (macOS 26 only at the moment, though - we&#x27;ll support more platforms over time, but for now are focusing on iterating the core product).No login required except for the AI generation features, which route requests to our backend. We are offering free credits on sign up so you can try out the AI generation as well.We&#x27;d love to hear your feedback!

HN