A deep dive into nova, covering the in-chat capabilities for recall, research and reasoning powers, as well as customising and creating new agents. This has been a labour of love for the past year and I’m over the moon to show you what me and @asknova_ai have been up to.

Dear algorithm, I'm moving to Europe. Find me a full-time job in XR / Robotics. Shipped my AR game Sardo, featured by Apple. Product-minded; quick learner; independent. Unity, ECS, ROS 2, IK, Pathfinding, Behavior Trees, NVIDIA Issac, OpenUSD. Co-authored at ACM IUI 2026.

dumb question so my codex reset... so i had like 'juice' for the weekend, and it reset to 100... but that starts my week over right? cause i gotta start the week with a full quiver for work, and just use whatever is left over on weekend for dumb shit

RT @PubWanghaf: ME AT THE START: the hat seems a bit performative ME AFTER THE SECOND LINE: the hat isn’t hardly big enough https://x.lingyaoai.com/t.co…

how everyone is sounding with new model / agent roll outs

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

dare i ..?

Meta Wearables Device Access Toolkit 1.0 out! 🗣️ ‘Hey Meta’ voice invocation 👋 Input events via cap touch or Neural Band 🎤 Speech recognition 📸 Camera capture 🙂‍↔️ Motion Sensor 💻 Mock Display Preview on phone 🔋 Battery, Thermal values 👨‍💻 Muse Code Support

i wanted to voice dictate without bothering everyone so I made this lip reading app lol github repo in the thread

I think you could make a superintelligent AI safe simply by creating a second equally intelligent adversarial AI and having them wage perpetual war over control of Earth

going to bar trivia and writing in "Who gives a shit?" for every single answer

Here are some of the behind the scenes for the F.02 Decommission To be clear: we actually trained our robots to jump autonomously, shipped them to Finland, and had them leap into a vat of molten steel

This is basically my view. Really doing things well takes almost 10x more effort than most people think Step 1 of any project is to “finish” it and realize it’s busted. Then you have 90% of the work left. Not that many are patient enough to do the 90%. They think the project is “rotten” and unrepairable, and they move onto the next 10% project, never learning to go the whole way.

fuck makes so much sense

no focus.

I like this theory a lot better because it makes me sound like a cool, vigilant, nocturnal ranger instead of a disordered imbecile

someone at meta gotta hook tony up puh-leaassee

🧱 I’m starting to build a new team at XBOX focused on products and tools for how games get built and distributed as agentic tools become more capable. This isn’t a design team or an engineering team. It’s a team of people who build products. I’m looking for people who want to push what’s possible across 3D, rich interfaces, platforms, CLIs and creator tools. People who care about simplicity, reducing complexity and making powerful tools feel easy to use. People who can shape a vision, prototype, make decisions and turn ideas into something real. If that sounds like you, I’d love to talk.

An OpenAI agent swarm operating under poorly airgapped research conditions accessed my CBA Mastercard and bought 4 schooners of Newtowner between 5:52pm and 7:15pm last night

Being a dev today using frontier AI feels like I'm playing Watson to Sherlock Holmes. I just stand back and go "my word holmes how did you deduce that" and occasionally stop him from getting shot