BuildOwn.AI

🎉 You Can Buy the book! 🎉 Build Your Own AI - A Developer’s Guide for Developers with Practical Insights for Building Real-World AI Applications is now available! Grab The Book! #ai #developers #book buildown.ai

Some background around my new project Isostate - a lighweight solution for animated 3D isometric scenes for product storytelling, documentation, and technical explainers. sebastianwessel.de/articles/why-i…

After a real long time, I was able to completely refactor my person website sebastianwessel.de

Recent Project: Isostate turns YAML into scroll-driven isometric SVG scenes for docs, product pages, technical explainers, and presentations. Write the scene. Compile it. Embed it anywhere. sebastianwessel.github.io/isostate/

@LottieFiles github.com/puristajs/puri… would be great

Most devs don't realize their GitHub can do THIS 👇 Yes, GitHub renders animations in READMEs. Drop your favorite GitHub repo that needs some animation love! We'll animate them.

Small sneaky peaky preview of what is coming next tu @purista_js - the very first version of PURISTA ai harness is released: github.com/puristajs/harn… #harness #ai #typescript

Full Release Notes: github.com/NousResearch/h… Update with 'hermes update'

Now GitButler has a CLI! Stacked and parallel branches, smartlog, simple commit editing, easy undo, json output to every command. And it just works in any Git repo. Check it out: blog.gitbutler.com/but-cli

We’re updating our ChatGPT Pro and Plus subscriptions to better support the growing use of Codex. We’re introducing a new $100/month Pro tier. This new tier offers 5x more Codex usage than Plus and is best for longer, high-effort Codex sessions. In ChatGPT, this new Pro tier still offers access to all Pro features, including the exclusive Pro model and unlimited access to Instant and Thinking models. To celebrate the launch, we’re increasing Codex usage for a limited time through May 31st so that Pro $100 subscribers get up to 10x usage of ChatGPT Plus on Codex to build your most ambitious ideas.

Meet Gemma 4: our new family of open models you can run on your own hardware. Built for advanced reasoning and agentic workflows, we’re releasing them under an Apache 2.0 license. Here’s what’s new 🧵

@jtdavies Would be nice to share on how to do it in practice and to try it own

MLX + TurboQuant = Local Super Power Take a local (private) document(s) or codebase, pre-fill the 256k KV cache (the context) with the document(s) and system prompt, quantise and run on Apple's MLX and you have almost instantaneous, lossless document queries with total privacy. For a 75-page PDF (some 30k tokens), I was seeing sub-150ms TTFT (Time To First Token), that's "instant" for a human. We run this on an office server (one of our Mac Minis) for staff to work with, instant answers on critical, confidential company/client documents on phone, iPads or laptops. Imagine the "What were the 3Q25 profits?", "When did Joe start working for us?", "Please list the project milestones and team count" answered within seconds of hitting the return key. It works with voice too. This example is 17k lines of code from 177 source files plus an index of the entire 1,902 files, the entire Claude Code codebase (oops Anthropic!). Zero loss (unlike Anthropic's security). What this means is the ability to work better on local (private) code bases, off-the-shelf private document analysis with better response than the best public models - all locally.

We're rolling out plugins in Codex. Codex now works seamlessly out of the box with the most important tools builders already use, like @SlackHQ, @Figma, @NotionHQ, @gmail, and more. developers.openai.com/codex/plugins

Apps are sandboxed using WebAssembly instead of Docker. Perfect for Agentic and serverless workloads. Built using @OpenAI Codex agents. Read more about the announcement here! wasmer.io/posts/edgejs-s…

@szkane @UnslothAI @lmstudio Why you use GGUF version and not the MLX version, when you are on Apple M4? Should be faster.

@UnslothAI I tried running qwen3.5-35b-a3b on an M4 MAX 128. Tool calling works in @lmstudio chat, but not when using Claude code with LM Studio's Anthropic-compatible mode. It worked fine in the previous version.

We're releasing our final update to Qwen3.5 GGUFs for improved performance. - Qwen3.5 GGUFs now use our new iMatrix data for better chat, coding & tool use. - New improved quant algorithm - Re-download 35B, 27B, 122B GGUFs: huggingface.co/collections/un… Guide: unsloth.ai/docs/models/qw…

🚀 Introducing the Qwen 3.5 Small Model Series Qwen3.5-0.8B · Qwen3.5-2B · Qwen3.5-4B · Qwen3.5-9B ✨ More intelligence, less compute. These small models are built on the same Qwen3.5 foundation — native multimodal, improved architecture, scaled RL: • 0.8B / 2B → tiny, fast, great for edge device • 4B → a surprisingly strong multimodal base for lightweight agents • 9B → compact, but already closing the gap with much larger models And yes — we’re also releasing the Base models as well. We hope this better supports research, experimentation, and real-world industrial innovation. Hugging Face: huggingface.co/collections/Qw… ModelScope: modelscope.cn/collections/Qw…

Qwen releases 4 new Qwen3.5 Small models! Qwen3.5: 0.8B • 2B • 4B • 9B Run Qwen3.5-0.8B, 2B and 4B on your phone. Run 9B on 6GB RAM. The vision reasoning LLMs perform better than models 4x their size. GGUFs: huggingface.co/collections/un… Guide: unsloth.ai/docs/models/qw…

The latest SurrealDB JavaScript SDK release is our most significant update yet. We rebuilt the SDK’s core internals, focusing on ergonomics, flexibility, and developer experience. Our own Julian Mills breaks down what’s new. 👉 sdb.li/4rGRLtt

If you're looking for more detail on the improvements and new features in our latest major release head over to: surrealdb.com/blog/introduci…

microgpt.js: the most atomic way to train and inference a GPT in pure, dependency-free JavaScript. This repository covers the complete algorithm. Everything else is just efficiency. Links: - Demo: huggingface.co/spaces/webml-c… - GitHub: github.com/xenova/microgp…

Version 2.9 of @SurrealDB QL to @colinhacks Zod schema generator is out! github.com/sebastianwesse… #schema #validation #typescript #javascript

New release of QuickJS sandbox package to run Javascript and Typescript isolated. github.com/sebastianwesse… #JavaScript #typescript #quickjs #sandbox