I've been making bespoke educational videos for my kid since Opus 5.5 released. The model is an amazing combination of programmatic animation and content planning. One approach I've found useful is asking the model to build a reusable embodied narrator that can point and look. This helps direct attention in the midst of complex content. Having it as a reusable library saves time and tokens, and avoids repeating the same animation mistakes. Here's a tech demo of one of these characters explaining itself. The narration is ElevenLabs v4, and everything else is javascript and canvas from scratch.

Games have shaped me for decades. #My9Games

If you missed it from yesterday, here are the ten steps I recommend for building cross-generational communities.

The 5.5 opus programmatic animations are impressive. I tried to create one like @pleometric's, with a loose prompt, no example images/video, and no animation or art libraries. The one-shot prompt asked for an animation in html and javascript with a vague description of Clawd watching Tiktok videos of his AI friends. It did not include a scene by scene breakdown or a list of the actual content. This cost 5% of weekly usage on a $100/mo plan, on high. It did write a reusable library of functions that might make future animations cheaper. It also helpfully included an mp4 export button in the generated .html, which I had not thought to ask for. Completely inspired by @pleometric's post.

My kid hit a hurdle in his reading homework. The passages were suddenly longer, more difficult, and he was losing interest because of the effort per task. I read a few of the passages and noticed myself re-reading some sentences because they were difficult to process completely in one pass. "Extended-duration human exploration missions that are now the focus of NASA will require extended life support capabilities." My kid reads frequently, but rarely encounters this denser, more academic style of writing. It wasn't impossible, just a slog. So, I asked Astra in Codex to (1) research the most prevalent academic sentence patterns in middle school content, and (2) make a slide deck with examples, diagrams, terms, and explanations. With that, he told me that 6 of the 18 patterns were effortful for him to read. The fourth screenshot was met with an "I hate it." Feedback in hand, I was able to build a bespoke small learning app to practice dense sentences and paragraphs. The text was shorter, harder, and without extraneous load from a tricky homework question. If he could parse the paragraph, the answer was obvious. He seems to be building his skill at reading this kind of text, although I misunderstood at least half of the problem. The app is giving him focused practice with unfamiliar syntax forms, but also teaching him to notice confusion and resolve it. I think this is called metacognitive monitoring and control. He's improving at that too. It is amazing how much easier it is to help my kid learn more, as I repeatedly gain access to better AI models. I've been building him bespoke little apps for years (since GPT-3.5 Turbo), and each major generation builds the apps better and faster.

Does spaced retrieval practice work in all subjects? New study suggests the honest answer is sometimes, and we do not yet fully know when. 🧵⬇️

"3-year olds are already self-directing their learning - through questions, exploration, and play." Yes, and letting them understand all these weird symbols everywhere in their life is a great way to further empower them to ask questions, explore, and play. I taught my kid to read at 3 with "Learn to read in 100 easy lessons", and it was amazing to see how much more of the world he could engage with. Books obviously, but also words on toy boxes, menus, instructions for games, warning signs, building names, etc. It's like a whole new sense flips on.

Your bookshelf makes you smarter Every time you walk past a book you've read, pause for a few seconds and recall 2-3 key takeaways This simple habit combines two powerful learning science principles: - Retrieval practice: actively pulling info from memory strengthens those neural pathways - Spaced repetition: these random encounters naturally space out your reviews but wait there's more When you recall those takeaways today, you're a different person than when you first read it new experiences, new lens This creates fresh pathways to that knowledge like building new roads to the same destination Your brain literally rewires itself with each recall, making that wisdom more accessible when you need it So yes, display those books proudly they're not just decor They're mini learning sessions waiting to happen throughout your day.

US education PK12 market numeracy: * there are about 4M children per grade level * total public school spending is about $1T == 20k/student/year * about 20% of that is special ed * total private school consumer spending, including prek, is about $100B

We've always been excited about self-play unlocking continuously improving agents. Our insight: RL selects generalizable CoT patterns from pretrained LLMs. Games provide perfect testing grounds with cheap, verifiable rewards. Self-play automatically discovers and reinforces reasoning strategies. We introduce SPIRAL, where models learn reasoning by competing against themselves in games, creating an infinite curriculum without human supervision. Training LLMs with self-play RL on Kuhn Poker improves math reasoning by 8.7% average. Just playing Kuhn Poker improves Minerva Math scores by 18.1 points! 🃏 🔗 Paper: huggingface.co/papers/2506.2… 🧑‍💻 Code: github.com/spiral-rl/spiral

GPT-5 shows remarkable robustness for production instruction-following. On IFScale—our benchmark testing 100s of simultaneous constraints—it maintains >90% accuracy* through 500 instructions. Huge leap over previous bests o3 & gemini-2.5-pro (~69%@ 500). *run on 1 seed, 5 ongoing

Take: Chain of Thought is a misleading name. It's really a "scratchpad". "Thoughts" are internal activations Imagine you're solving a problem and have a scratchpad. Reading the pad gives me info! You *can* avoid writing down key thoughts. But it's a handicap. Real but fallible

OpenAI's Agent mode has a roundabout live interaction mode. I gave it a google doc with "anyone with the link can edit" enabled, and it successfully picked up new instructions and wrote incremental updates to the doc, in the middle of a single agent run. The doc explained to check back for new instructions frequently, and to post updates. It was surprisingly bad at google docs formatting though. Plaintext or markdown would be better.

When will AI systems be able to carry out long projects independently? In new research, we find a kind of “Moore’s Law for AI agents”: the length of tasks that AIs can do is doubling about every 7 months.

Building this app has been a journey. Balancing work and going indie, I’ve rewritten it four times to control its scope. I think I’ve finally reached a good stopping point—for now. Materia AR is now in the App Store #buildinpublic

We announced @OpenAI o1 just 3 months ago. Today, we announced o3. We have every reason to believe this trajectory will continue.

When people age, they accumulate biological damage that eventually reaches a tipping point and leads to a cascade of catastrophic health issues. The same thing happens to students learning mathematics: a death spiral caused by compounding knowledge gaps. Students accumulate knowledge gaps as they progress through math, and they stop taking math classes once the number of gaps reaches a tipping point and spirals out of control. Knowledge gaps can form in a variety of ways. To name a few: 1) A student may get stuck on foundational topics yet still be required to complete homework on more advanced topics, leading them to scrape by without really understanding the subject matter. Even a grade of B+ or A- means that there are things in the course that the student never completely grasped, much less mastered. 2) Students typically do not review material learned in previous years (unless it just happens to be practiced implicitly while attempting to learn new content), and they often do not even review material from their current year unless they are preparing for a test. This leads them to forget what they’ve learned -- often so severely that they need to re-learn it from scratch when it shows up again in the future. 3) Gaps can also be created if a student takes a course that is watered down or otherwise not comprehensive. When a future course assumes prior knowledge that the student never actually learned, that’s a gap. Now here’s the real kicker: Gaps beget more gaps. Once you have a gap, you are unable to fully understand any new information further down that learning path. The gap proliferates. Consequently, once a student amasses a critical number of gaps, things spiral out of control and a vicious cycle kicks off. The cycle begins with a student trying to imitate procedures cookbook-style, without really understanding what’s going on, because they can’t intuitively grasp any of the new material that they’re being taught. Soon after that, they find themselves unable to solve any problems that involve critical thinking or many steps. Finally, they stop taking math classes because they feel it’s impossible to succeed no matter how hard they try. The student may interpret this situation as “I’m not smart enough to learn more math” – when in fact, their mathematical lifespan could have been extended simply by having their knowledge gaps detected and repaired.

Eric Schmidt says in the next year, AI models will unite three key pillars: very large context windows, agents and text-to-action, and no-one understands what the impact will be but it will involve everyone having a fleet of AI agents at their command

The reason I’m insanely bullish on AI is that since starting Box, we have never seen a bigger shift in how we can work with our enterprise information than today. AI completely revolutionizes how we can work with enterprise information. Since the mainframe era, it’s been relatively trivial to work with our *structured* data in an enterprise. We could query, compute, synthesize, summarize, and analyze anything that could be structured in a database - i.e. the data sitting in our ERP, CRM, and HR systems. But it turns out this is only a small fraction of our corporate information. If you were to “weigh” the amount of data inside of an enterprise (in the form of raw storage), roughly 10% of it would be structured data, and 90% of it would be unstructured data. And our content — things like our documents, contracts, product specs, financial records, marketing assets and videos — makes up the vast majority of this corporate data. Yet for essentially the entire history of computing, we haven’t *really* been able to make sense of this information unless a human is involved. Of course we can store it, send it, share it, and search for it — but deeply understanding what’s inside this information in a way that computers can interact with intelligently has been near-impossible. Well, for the first time ever, generative AI actually lets us talk to our unstructured data. Multimodal models especially allow us to process this content using a computer and essentially perform any task that a human can, but at infinite scale and speed. This is utterly game-changing when working with information in the enterprise.  Instantly, our content goes from being digital artifacts that get touched once in a while, to a digital memory that anyone in the enterprise can tap into always. All of a sudden instead of the more information you have making things harder to find and make sense of, the opposite becomes true. And we enter a world where your digital information becomes one of your most valuable resources. When we can turn our content into valuable knowledge, everything about how we work changes. A new employee instantly has access to the same expertise of someone who’s worked at a company for 15 years; when you can understand what’s inside of content — like contracts, invoices, or digital assets— and extract its structured data, you can automate nearly any workflow; and AI can let us classify and protect content with a level of precision that’s never been possible before to prevent threats and risks across the enterprise. This is simply the biggest change we’ve ever seen with how we can work with our data, and this is what we’re building with Box AI. In 1945, Vannevar Bush wrote a seminal article which outlined eerily insightful predictions, including the idea of the “Memex”, a new device “in which an individual stores all his books, records, and communications, and which is mechanized so that it may be consulted with exceeding speed and flexibility. It is an enlarged intimate supplement to his memory.” The vision laid out imagined a future where the more knowledge and information your “computer” had, the smarter and more informed you would become. While many aspects of PCs, mobile devices, and the cloud eventually resembled this early vision, the seamlessness in how we could work with our information never quite played out.  Until today.