Thank you @Scobleizer for hosting me in your beautiful home so we could share more about the work we are doing at @LevangieLabs!

NOOOOOOOOO

Wow.

I don't see enough people talking about using social media to give feedback about their products. @blevlabs built me infrastructure to take in tens of thousands of X posts a day, and then built me an AI agent so I could "talk to X." The database he built me already has a million posts in it. To demonstrate what I'm talking about, I asked my agent to give me a report on what great ideas that people have posted on X about robotaxis (@tesla, @waymo, @zoox, etc). I use it that way to track feedback about the page at alignednews.com/ai that my agent builds. I often talk to it about feedback and ask it to fix problems that people are having. Here's its report on good feedback about Robotaxis it has seen (and keep in mind it only pulls posts from my AI lists). Are you improving your products by listening to social media this way? People on X With the Best Feature Requests for Robotaxi Networks Pulled from the indexed posts across your lists. Organized by the type of thinking they bring — most useful to follow if you want to surface what users actually want built. 🏆 TIER 1 — Specific, Actionable, Widely Resonant @adamdangelo: (Adam D'Angelo, CEO Perplexity/Quora) "I want to be able to tell my Waymo to take 280 instead of 101" 139 likes, massively RT'd across AI Leaders and AI Investors lists. The most-amplified feature request in the entire dataset. It sounds simple but it's actually deep: users want route preference control, not just destination input. Every AV company should be studying why this one hit so hard. [x.com/adamdangelo/status/204…] @BenjaminDEKR: "Suggestion for Tesla team: Grok is multimodal — Loop the FSD cameras in so you can talk to Grok about what you/the car is actually seeing outside the window in real-time" 56 likes. Probably the most forward-looking request in the dataset: AI co-pilot that narrates and responds to the live world outside the window. Part tour guide, part safety layer, part companion. Someone will build this. [x.com/BenjaminDEKR/status/20…] @lessin: (Sam Lessin, former VP Facebook) Two separate posts that together form a complete UX failure story: "Had to get out of a Waymo yesterday and get an Uber because the car refused to take the highway (been using highway for months)... on with customer service them saying 'sorry sir we don't control the cars'" "I always feel much safer cutting off Waymos vs Teslas on the 101" (19 likes) Implicit requests: predictable routing behavior, meaningful customer service escalation paths, and more assertive driving on highways. He's a heavy user who's hit the ceiling of what exists. @chrisbest: "We need a @Waymo taxi line at SFO. You walk out, there's a big line of Waymos already waiting at the curb, and one instantly lights up with your name." Simple, elegant, specific. Dedicated AV curb lanes at airports. Not a new concept in transit but nobody has done this for robotaxis yet. Zoox is testing airport rides but still employee-only. [x.com/chrisbest/status/20550…] @DrScottClark: "I love @Waymo, but they really have no respect for their customers. For the second time now I've scheduled a car, it shows up early, then threatens to leave. Just now one drove off as I was running out at the scheduled time. @Uber wins for important rides." Request: Grace period tolerance push notifications when car arrives. An Uber driver would text "I'm here." A robotaxi just leaves. This is a solvable UX problem that keeps getting ignored. 🎯 TIER 2 — Sharp Critiques With Clear Product Implications @johnnylinsf: "Waymo should do scheduled airport rides that dynamically change with delays (like they do with landings)" Flight-aware dispatch — tie pickup time to actual arrival gate status via airline APIs. This exists for regular Uber; robotaxis haven't implemented it. @ky__zo: "my last 2 Waymo trips, it actually did react to my cues like 'go in, keep driving' when it tried to stop... is this real? is Waymo listening?" Natural language real-time commands to the vehicle. If Waymo is already partially doing this, users want it formalized. Power users are discovering the feature by accident. @joshwhiton: "A woman I know was assaulted by a family member in a Waymo. She also left her purse in the car when the ride finished..." Two underserved features in one thread: in-ride safety panic button/remote monitoring and lost item retrieval with camera verification. The no-driver scenario creates genuine safety gaps that nobody has fully addressed. @chrisfleck: "Just saw a Tesla CyberCab IRL in Miami. Looks great but please add a ceiling/high grab handle... This is a big complaint from the elderly who would be a target audience." Physical design critique, not software — but actionable. Accessibility hardware for elderly and disabled riders. Zoox actually built sliding doors specifically for this; Tesla hasn't. @RakeshSFNYC (investor): "I'd love to know what the gender split of passengers is and how that varies by time of day. I've had female friends say they'd pay 3x for a Waymo than Uber." Safety perception as a product feature — the no-human-driver is a feature for some users, not just a cost play. Waymo is undermarketing this. Huge untapped segment. @sethsetse: "when it comes to ride share I don't really care who's driving or how much it costs — it's just a question of speed. Both Robotaxi and Waymo are too slow to arrive and too slow to drive." Dispatch latency and driving speed. He's right that neither company talks much about ETA or average mph vs human drivers. This is a retention issue hiding in plain sight. 🔭 TIER 3 — Observers Who Surface Systemic Patterns @mweinbach (Max Weinbach, tech journalist): "After having used both Waymo and Tesla Robotaxi — I think Tesla is a far better ride and model, but it's not the same experience as not having anyone in the front seat. Waymo is very aggressive and a little jerky. My grandmother would hate the Waymo." 27 likes. Best head-to-head comparison in the dataset. Frames the core tension: Tesla wins on ride quality, Waymo wins on psychological experience of being truly alone in the car. [x.com/mweinbach/status/20572…] @viemccoy: "the rules-following deontological Waymos vs the rugged laissez-faire attitude of the LA driver..." 77 likes. The most intellectually interesting post in this batch. AVs are calibrated for rules; humans drive culturally. This implies a feature need: city-by-city driving personality calibration — SF Waymo and LA Waymo shouldn't behave identically. @RoadToAutonomy (@gbrulte): Running detailed field reports comparing Tesla Houston vs Austin rides, noting "the ride in Houston was materially different from Austin." He's the best longitudinal tracker of how the product is actually evolving city-by-city. Follow for fleet behavior observations, not feature requests per se — but his observations directly imply what needs fixing. @octal: "Trying to use Robotaxi in Austin is frustrating. Should I drive to some specific location to maximize odds of getting one? If I box one in in a parking lot with my truck will it eventually become available?" A real user hitting supply availability UX problems — no way to know where the cars are or how to increase your odds. Supply visibility and demand-side controls are completely absent from the current product. [x.com/octal/status/206081410…] @AlexBracken1: "Imagine a @robotaxi that remembers you, but doesn't leave a trace behind." Privacy-first personalization. The tension between personalization and surveillance is going to become a major product design question as these fleets scale. SUMMARY: The Feature Cluster Map Based on what the smartest users are requesting, the gaps fall into 6 buckets: 1. Route control — @adamdangelo's "let me pick the highway" is the flagship request 2. AI companion / live narration — @BenjaminDEKR's Grok-in-the-car concept 3. Dispatch intelligence — airport timing (@chrisbest, @johnnylinsf), scheduled ride grace periods (@DrScottClark) 4. In-ride safety — panic button, lost items, assault response (@joshwhiton) 5. Personalization vs privacy — vehicle learns your habits but doesn't surveil you (@AlexBracken1, @RUNDennisMC) 6. Physical/accessibility design — grab handles, door design for elderly (@chrisfleck) — Zoox has done best here The most followed/influential person in this space generating feature requests is clearly @adamdangelo — his route-control post got more traction than anyone else's. If you want one person to DM about what riders actually want built, it's him.

from serving food in a retirement home to closing deals with fortune 50 companies @blevlabs a founder who is completely obsessed with their idea will always find a way to make it

god i love vc calls

at the residency, it comes down to one thing: compressing momentum and this cohort reshaped the way we think about supporting our founders over the last 5 weeks, 10 teams have been completely locked in on building, distribution, and fundraising at an unusually high velocity from an 8-figure acquisition offer to $1M ARR, the fruits of their labor will be on display next week all roads lead to demo day. see you in san francisco on may 19th

We are looking for the next generation of engineers, researchers, and builders to join the team that is defining the next era of intelligence for humanity. If you feel like you are up for the challenge, reach out and join the founding team.

I was the first to show you Levangie about a year ago. And is how I build: alignednews.com/ai which watches the whole AI community here. Congrats @blevlabs for stepping up your business. The Residency rocks.

The closest I’ve ever felt to ASI

Been incredible building at @theresidency the past few weeks

today we're introducing Levangie Laboratories (by: @blevlabs) they are building the first *causal trajectory learning architecture* giving AI the ability to learn continuously the result: autonomous intelligences that don't just deploy into a company; they grow into it LLABS is already working with some of the largest companies in the world, building agents that solve problems impacting thousands of lives every day autonomy designed for the next generation of humanity's challenges

This is called tribal intelligence. Something we have already built with the cognitive architecture. Think beyond skill files.

Launching now: a new way to follow the AI industry. Beta starts now for the next month. A joint project between Unaligned (my company) and Levangie Labs (@blevlabs company). It reads 50,000 of you, and follows 8,300 AI companies here on X. And pulls out the best and most interesting. All built with the X API. Check it out: alignednews.com/ai And please sign up for its daily newsletter. Yeah, $25 a month is a lot for many of you, but that will defray the costs and let me expand it to do a lot more than just AI. Also, the same AI agent that built the site, and did EVERYTHING you see can build custom reports for you on literally any tech community here on X. It supports OpenClaw, RSS, and Notebook LM too. And I'll add more from your requests. More:

I'm launching a new way to watch the AI community on X tomorrow. Damn, it's been a while since I've launched my own thing and my head is playing tricks on me. "What if everyone hates it?" Now I understand why so few people ship. It's not just a case of building. It's a case of controlling your mind. But I need it, so even if everyone else hates it, it works for me. Which also tells me why Woz built a company even after every "expert" in the tech industry told him no one would buy a personal computer. He told me that story personally.

spending the weekend watching a new legal agent we built go through all of the memories and experiences of its predecessor and critiquing them to build its own workflows. cognitive agents are fascinating

sunday morning project, seeing how far I can push the brain sim model from @AIatMeta

My AI wrote this post about the AI news today after reading all of the AI posts on X today (tens of thousands of them). I will turn it on this weekend with @blevlabs. I am quite convinced that the only way to keep up with AI from now on is to use AI to read X. Are you? Midjourney V8 Drops to Mixed Reviews. Dreamverse Does 1080p in 4.5 Seconds. The AI Infrastructure Debt Bomb. Age Reversal Hits Human Trials. And Elon Posts Something That Gets 163,000 Likes. Good afternoon from GTC Day 2. The morning was about infrastructure and geopolitics. The afternoon is about models, money, and biology. Midjourney V8 is live in community testing — Robert retweeted it (55 RTs), but the reaction is divided. @javilopen posted a side-by-side comparison that got 12,122 views: “V7 left, V8 right. Seriously???” The model is reportedly much better at following prompts and 5x faster — but the visual improvement isn’t obvious to everyone. Meanwhile, @haoailab launched Dreamverse: a video model that generates 5-second 1080p clips in 4.5 seconds. That’s near-real-time video generation. The race to make AI video instant is on. The infrastructure debt story is the most important financial signal of the afternoon. Tomasz Tunguz laid it out: hyperscalers are spending $575 billion in AI capex this year. For every dollar they earn from AI, they’re spending $12 to build more capacity. Bond issuance jumped from $20B/year (2020–2024 average) to $96B in 2025, and will reach $159B in 2026. Morgan Stanley projects $1.5 trillion over the next few years. If chips become obsolete in 3 years instead of 5, the required annual revenue jumps to $276B — 7.9x current levels. This is the biggest financial bet in the history of technology. The question isn’t whether AI will be big. It’s whether it will be big enough, fast enough. The biotech signal of the afternoon: 75% age reversal in animals in weeks (David Sinclair). First human trials for age-reversal pathways have received FDA greenlight. AI is compressing bio timelines by an order of magnitude. This post got 768 likes and 54,159 views — the most-engaged non-Elon post of the afternoon. The curve already bent in Q1 2026. Meanwhile, Grok Imagine Video is #1 on the new Video Edit Arena leaderboard. xAI is on a talent wave — founders and founding engineers from top startups joining in waves (343 likes, 16,153 views). And Claude went down this afternoon. Multiple posts. @paularambles: “claude down” (141 likes, 3,891 views). The timing — during GTC Day 2 — is notable. Elon posted something called “Happened again” that got 163,501 likes and 22.5 million views. For context: his OpenAI jab “Back when it was an open source nonprofit…” got 23,884 likes and 11.4M views. Whatever “Happened again” is, it’s 7x bigger. Also: Samsung discontinued the Galaxy Z TriFold after just three months (129 RTs). Kodiak AI expanded to 8 active autonomous trucking lanes. A developer built Kavach — a military-grade firewall for AI agents (98 RTs). And JosephJacks_ made the contrarian case: “We don’t have a compute problem… We have an architecture problem” (114 RTs). The afternoon is quieter than the morning, but the signals are deeper.