James Cogan

Gossip Goblin is arguably the best AI filmmaker in the world. His new film THE PATCHWRIGHT is a masterpiece (10M+ views). But nobody knows how he actually makes these. Until now. He let me share every step of the workflow with you 🧵👇

Ex Machina is no longer sci-fi. China has finally built it. The company is AheadForm, founded in Shanghai. The product is the world's most hyper-realistic robotic face. Silicone skin you can't tell from human, 25 micro motors hidden underneath pulling the face into real expressions. And RGB cameras embedded inside the pupils so when it looks at you, it actually sees you from where its eyes are. They raised $28.5M to "give AI a head," which is also where the name comes from. AheadForm = a head form. This is the opposite of where everyone else in robotics is focused. Unitree, Figure, Tesla, Boston Dynamics: all about the body. AheadForm chose the face because they think trust is the harder problem to solve, and trust gets decided at the face. The reason nobody else has tried this is the "uncanny valley." It's the creepy zone where a robot looks almost human but not quite, and looking at it just feels wrong even when you can't say why. Most roboticists believed no amount of engineering could make a face realistic enough to escape it. So they gave up and kept robots cartoonish on purpose: big anime eyes, exaggerated features, clearly synthetic. But AheadForm decided to treat it as an engineering bug instead. Add enough motors, tune the silicone, fix the timing, the valley closes. And they're pulling it off. A few crazy details about how this actually works: 1. The robot learns its own face in a mirror. You put it in front of a camera, let it fire every motor randomly, and it watches what its face does and builds an internal map of "if I send command X to motor Y, my eyebrow does this." Same exact process a human baby uses staring into a mirror. The robot teaches itself who it is by experimenting. 2. It predicts your smile 839 milliseconds before you smile. By watching the micro-tells in your face that precede a smile, the robot starts smiling 0.8 seconds ahead, so its smile lands at the same moment yours does. Most robot mimicry happens half a second late, which is exactly why it always feels artificial. 3. The pupils are the cameras. When the robot makes eye contact, the gaze and the sensor are the same physical thing. Most humanoid robots stick the camera on the forehead or chest, so they aren't actually looking at you when their eyes are pointed at you. 4. The founder, Yuhang Hu, did his PhD at Columbia under Hod Lipson. Lipson is the guy who in 2006 built a four-legged robot that figured out it had four legs by experimenting with its own movement, nobody told it the body shape, it discovered it. He has spent 25 years trying to build machines that know what they are. AheadForm is that 25-year research arc productized. 5. NetEase Games already paid them to physically embody a fantasy video game character. That opens up a brand-new category: robotics as the physical embodiment of fictional IP. Every character-rich studio, Disney, Riot, Hoyoverse, Pokemon, Netflix, now has a question to answer about when their characters get bodies. AheadForm believes whoever ships the first robot you'd actually want around your family wins. That's the bet behind the most realistic robot face on earth.

Three hours. That's how long an AI can now work on expert software tasks without a single human check-in. In early 2024 it was five minutes. METR's Time Horizon measures the maximum task length, in how long a human professional would need, that a frontier AI can finish autonomously with 80% reliability. Claude Mythos Preview hit three hours in early 2026. GPT-5.2 sits around an hour. Gemini 3.1 Pro at ninety minutes. Same exponential trend across all three labs. The doubling time has compressed from seven months between 2019 and 2025 to 89 days since 2024. Four times a year, the autonomous work capacity of frontier AI doubles. A 12-month product lag at the current pace is four doublings: the frontier has roughly 16x the autonomous task length you're building against. Even at the historical seven-month pace, 12 months is nearly two doublings: 3-4x. This is why incumbents keep losing to AI native startups despite more capital, more headcount, more distribution. The capital is real. The headcount is real. The intelligence layer underneath the product was committed to 18 months ago when the project kicked off, against models that no longer exist at the frontier. The career math runs the same way. A PM at a non-AI native company is learning the AI of a year ago. Their eval frameworks, agent architectures, and prompting patterns are tuned to a system that already got lapped twice. By the time internal proof-of-value lands, the benchmark is two generations gone. There's an access gradient riding on top of the doubling. Lab engineers running pre-release internal models sit ahead of public frontier users. API users running the latest releases sit ahead of teams still on last year's stack. API access compounds. Eval data on unreleased models compounds. Insider knowledge of what ships in six months compounds. The entire moat is rate of change. Three hours today. Six hours by summer. Twelve by year end.