Ever wondered what’s hidden inside your favorite tech?
With OpenAI ChatGPT (or any other state of the art LLM), you can turn complex products into stunning exploded-view drawings, revealing their components, structure, and how everything fits together.
From concept to visual breakdown, AI makes engineering exploration more accessible, engaging, and fun!
#OpenAI #ChatGPT #ExplodedView #EngineeringDesign #AIInnovation #ProductDesign
🤖 Made with AI
The future of human-computer interaction is officially here. Meet Griffin by Tavus, the world’s first Human Interaction Model (HIM) designed for real-time, face-to-face conversations. In live tests, an astonishing 48% of people thought it was a real human on video! Watch the Introducing Griffin videos to see it in action -> tavus.io/griffin
#ArtificialIntelligence #MachineLearning #TechNews #VideoAI #Innovation
After testing Atomic Chat on Windows and macOS, it’s my pick for the most polished local LLM experience. Ollama and LM Studio paved the way; Atomic makes setup easy, with a beautiful UI, a local API, and simple access to your model from another device. Really impressive -> atomic.chat/
#AtomicChat #LocalAI #OpenSourceAI #Ollama #LMStudio #LLM #SLM
Jadranko Tomic retweeted
I still don't understand why everyone is still running agents in a line. I switched to graphs three weeks ago and my fleet finished in the time my single agent used to spend on step two.
what slows every agent system I have seen is not intelligence. it is geometry. and almost nobody is talking about it.
one engineer used this to rewrite 535,000 lines of code in 11 days. a manual rewrite of that scale could take close to a year. it cost $165,000 in tokens. the graph was not cheap. it was just faster than a human year.
a node is one agent with one job. research one competitor. review one file. check one claim. the moment a node owns two independent jobs you lose the ability to parallelize them cleanly, verify them independently, and debug them in isolation. an edge is a dependency. it only exists when data actually moves across it. everything else is a fake edge. a wait you invented that costs time and produces nothing.
find the fake edges and the line collapses into something wider. jobs that can run at the same time run at the same time. what used to take the sum of forty steps now finishes in the time of the slowest layer.
the pattern behind every serious agent system looks like a diamond. fan out to gather breadth, one agent per angle, all at once. reduce with plain code, no model tokens spent. verify with a fresh skeptic on every finding. synthesize once from what survived. Claude's own research feature uses a very similar pattern in production.
the part nobody warns you about: the verifier needs clean context. give it the same conversation the worker had and it is not checking anything. it is nodding along to itself in a different window. a graph of agents sharing one context is a single loop in a costume. it breaks the same way, just later and more expensively.
one rule that holds at every scale. a worker and its verifier must never share a context.
your agents are not too slow. they are waiting in a line that did not need to exist.
full guide in the article. save it before you build your next agent from scratch.
Jadranko Tomic retweeted
The new Surface Duo. There’s a new way to get things done. Available today: msft.it/6012TtMgr #DoOneBetter
A new way to get things done.
The New Surface Duo. With two screens connected by an innovative 360° hinge and a mobile experience that combines the best of Microsoft 365 with your favorite Android apps.
Jadranko Tomic retweeted
GPT-6 Astra设计FPV无人机飞控 PCB全过程记录,从电路原理图到 PCB 布局、走线、元器件摆放,都是Codex里的GPT-6在 KiCad 里直接操作,我可以看到它一步步画出来。
画完后它自己运行 ERC、DRC,检查问题,再修改电路和布局。
最后完成了 F405 六层飞控板的设计,还导出了 Gerber、钻孔、BOM、贴装坐标和 STEP 文件,能直接打开 3D 看整块板子的效果。
整个设计过程,总耗时3 小时 13 分 56 秒,总token消耗量约为51,900,896个(约5200万个),模型思考强度为高。
目前还没打样,实际能不能稳定工作,还要上板测试。但从描述需求到画出整块 PCB,这个过程已经挺让我惊叹了。
#AI #PCB #KiCad #Codex #GPT6 #Astra
Jadranko Tomic retweeted
New TIL on using Blender with coding agents on macOS: til.simonwillison.net/llms/b…
GPT-6 Astra (medium):
> Use the already install /Applications/Blender to render a scene of a pelican riding a bicycle
> OK add a background and a lot of flair
> OK make it a whole lot better

ALT A 3D illustration of a white pelican cycling along a seaside boardwalk at sunset. It wears a cream boater hat and a coral scarf, with wings on the handlebars and long orange legs reaching the pedals of a turquoise bicycle. A wicker front basket holds pink and white flowers, and three balloons float behind. Pastel bunting stretches overhead between palm trees. Striped beach huts stand beside a teal sea with a small sailboat, beneath a large peach-colored sun. The scene has a softly lit, toy-like style.
GPT-6 Astra - OpenAI’s latest breakthrough is next-level!
Top notch AGI benchmarks, unstoppable cybersecurity, and lightning-fast reasoning. The next level of AI is here -> openai.com/index/gpt-6-astra…
#GPT6Astra #AGI #OpenAI #FutureOfAI #AIRevolution
Muse Glimmer - Meta’s new open-source, 30B-parameter agentic AI model >>>designed<<< to run locally on your device. From coding to multimodal reasoning, it’s built for speed, efficiency, and offline capability -> research.meta.ai/blog/introd…
#AI #OpenSource #MuseGlimmer #LocalAI #AgenticAI
AI in August 2026: A Personal Checkpoint - Reflecting on LLM's journey from ChatGPT’s breakthrough to today’s transformative impact. Where we came from, where we are now, and what’s next? Let’s explore it!
Who is the King of the Local LLM AI (Inference)? -> limitededitionjonathan.subst…
#AI #aiinference #apple #mlxlm #localllm #llm #slm












