DevAnywhere.io

The biggest mistake in AI education is automating the part where the child learns. The questions. The wrong turns. The “wait, let me try again.” That’s the part gakku is built around. @gakkuai helps kids aged 6-16 practice writing, speaking and thinking through live conversations with Raku, its AI learning companion. What interests me from a product-design perspective is what happens when the child changes their mind. Having small kids myself, I know this happens a lot. A learner can interrupt, revise an idea or make a choice on screen. Raku has to adapt while keeping the conversation, visuals and mission progress in sync. The interface becomes part of the thinking. Ideas take shape on screen, and the child’s choices shape what happens next. That’s a much more interesting design problem than generating a good reply. The system has to follow the learner’s intent, remember what came before and decide when to ask, act or wait. For me, the design challenge is knowing how much help to give. Too little and the child gets stuck. Too much and the system takes over the decisions they need to practice making. The child still has to explain, choose and revise. The interesting bet here: the time spent thinking is the value of the product. When AI can generate almost any answer, helping someone develop their own becomes a lot more interesting. Currently trying this with my 6yo at home, will report back on how it goes.

Michio Kaku has a blueprint for a time machine. You just need the energy of a star. Then you hit the grandfather paradox. Time travel with Michio Kaku on Hanselminutes. Full episode: hanselminutes.com/101

Engineering Managers, this one's for you! 💛 That gap between Product and Engineering? It's not a talent problem. It's not a people problem. It's an understanding problem. And understanding is totally learnable. Yay! 🧵

had a lot of fun talking with @HarryStebbings about all things ai one line of questioning we went done - vertical vs horizontal agents, and how to build them im bullish on vertical agents, and i think you can create differentiation (from horizontal agents) in three ways: 1/ context: prompts, skills, tools - all of this is specific to your domain, pretty easy to provide, and gives domain specific context to the agent 2/ harness: harder to tweak than context, but can alter fundemental behavior of the agent 3/ model: hardest to tweak of all, but obviously changes behavior greatly i think most agent engineers these days are still tweaking 1 and 2 (in that order) nb: regardless of what layer you tweak at, as the base models change you should revisit your context/harness/model every 3-6 months (and generally remove cruft that is no longer needed) youtube.com/watch?v=1jDCPEHw…

Let's talk a little more about Margaret Hamilton because she deserves it In 1961, Margaret Hamilton was tackling massive systems, having previously wrangled room-sized computers that blared like a foghorn whenever they crashed. Her fix wasn’t just to patch the bug. Everytime there was a crash, she took a Polaroid of the programmer who wrote it, and a note on the mistake. That way, if it ever happened again, they wouldn't be starting from scratch. They could note patterns and the last person who triaged that failure could help. This is a critical aspect of what she gave us. She didn’t stop at fixing errors. She studied their patterns so she could see them coming. She called them “the enemy,” and she meant it. Initially, when she was working on failure modes, higher-ups were errors wouldn't happen she actually named her program “Forget It.” But failures did happen. And her mindset, and discipline sent men to the Moon. Her Apollo software was built to expect the unexpected, and on Apollo 11 it recognized an overload mid-landing and kept the critical tasks running. Every postmortem, every bug tracker, every “let’s make sure this never happens again” carries a little of her in it. Thank you, and rest in peace, Margaret Hamilton 🚀

Kevin Rose (@kevinrose) on the coming “headless” era of software.

💥 I'm extremely excited to keynote AGNTCon in San Jose in a few weeks! I'll be speaking alongside legends like @timoreilly, @dsp_, and @techgirl1908 My talk will be on the future of the Agentic Web. See you there! events.linuxfoundation.org/a…

The only person who ever reads your pull request description is you, three months later, trying to work out why you did any of it.

English is the new programming language. So what’s still worth learning? Vocabulary. Architectures Design patterns Refactoring techniques Security protocols Performance optimizations UI/UX patterns The greater my technical vocabulary, the more precise my prompt.

Every one of my mathematician friend sees beauty in the numbers, shapes and the natural phenomena they work with. Who defines beauty in the age of machines?🤔

NASA found a nebula shaped like a heart 📷 📷:NASA

Your mind will follow whatever you feed it. Want better thoughts? Consume better things.

Very sorry to hear this news. 😥 I never had the chance to meet Margaret Hamilton, but her contributions to the flight software that got us to the moon are legendary. I love this image of her standing next to the printouts of the Apollo code.

Ben Affleck reveals he writes Python, understands convolutional neural networks, worked extensively with GPUs, and used his celebrity status to get private looks at Google and OpenAI’s video models “I’ve always been kind of into computers since I was young. Then, when film started to move from analog film to digital, I became more interested in that aspect of it. The visual-effects workflow for many years has included machine learning, so I can write pretty shitty Python scripts and stuff like that. “With convolutional neural networks, which were the precursors to what the transformer can do, which is much more computation simultaneously, you would do things like look at what’s called a tensor. That’s the numerical translation of a visual image in numbers, like the batch number, the frame number and the red, green and blue values of each pixel in each frame. It’s just that simple. That numeric is called a tensor. “You’d use a convolutional neural network to identify patterns that reveal what’s called edge detection or feature extraction, which is identifying patterns well enough to know, this is where the window ledge is, so we can more easily take the green-screen image out and replace it with something. “That was familiar to me early on because, prior to Artists Equity, I had a small visual-effects company. I’ve worked with GPUs a lot too. The visual-effects guys said, ‘Hey, you should see. There are a couple: Google and this other company, OpenAI, are doing really interesting stuff with transformers in video.’ “I’ve learned that I can actually just call up and go, ‘Hey, it’s Ben Affleck. Can I come see what you’re doing?’ Sometimes people say yes, to my astonishment.”

Quality software doesn’t break, doesn’t demand attention, knows its limits, and fixes fast. @almonk is a fine builder of quality software, recommend.

I'm speaking at @CommitYourCode this year! Get your tickets sooner rather than later (they're only $40) so that Danny doesn't have to scramble to figure out logistics at the last minute.