Conference talk by Kwindla Kramer (Daily) arguing that AI agents are an early-stage primitive, analogous to web pages in 1995, and that the real opportunity is AI native software built on top of them. Using Vannevar Bush's 1945 essay "As We May Think" as a starting point, the talk surveys computing history—programming languages, 1960s interactivity, 1970s abstractions, the personal computer, and VisiCalc as a counterexample to technological unemployment—before demonstrating new agent primitives via Gradient Bang, a multiplayer game built around LLM interactions and hundreds of concurrent inference calls, exercising async non-blocking context compression, long-running context-sharing subagents, progressive skills loading, dynamic interface generation, and conversational voice. # Channel Identity Observations: AI Engineer World's Fair Talk — Kwindla Kramer, Daily ## Explicit Self-Descriptions by the Speaker - **Speaker and employer**: "My name is Quinn La Holman Cramer. I work at a company called Daily." - **Company scope claim**: "We make developer infrastructure for real-time audio, video, and AI." - **Product/framework claim**: "We're the team behind Pipe Cat, which is the most widely used framework for building voice agents today. Pipe Cat is open source and vendor neutral." - **Named customers claim**: "It's used by companies like AWS and Nvidia and Anthropic and thousands of startups and scale-ups and enterprises." - **Event context**: "Welcome to the voice track at AI Engineer World's Fair" — establishing the talk's venue and audience framing. ## Intended Audience - **Developers and AI engineers**, evidenced by the greeting to the "voice track" audience and framing: "a lot of the AI engineering work we're all talking about this week is focused on building a full coherent software stack for AI agents." - **Practitioners already building agents**: "at the moment we're building agents and we're having a lot of fun doing it" — the speaker assumes shared hands-on experience. - **Historically informed technical audience**: the talk assumes familiarity with figures like Vannevar Bush, Sketchpad, VisiCalc, and Star Trek-era computing without basic explanation. ## Claimed Scope of the Talk - **Stated agenda**: "what kind of agents we're building today, including voice agents, but not just voice agents, and what I'm interested in building next... in the context of the roughly 80-year history of digital computing." - **Forward-looking thesis**: "we're going to chart a path to a new fully AI native software that comes after agents and agents plus plus." - **Personal experience claim**: "I was a baby programmer in 1995... I co-founded a startup with John [Underkoffler] in 2006 to make the Minority Report interface into a commercial product." ## Observable Presentation Patterns - **Heavy use of historical framing and archival media**: extended references to Vannevar Bush's *As We May Think* (1945), Apple's *Knowledge Navigator* (1987), Star Trek, 2001, Minority Report, and Iron Man, with embedded video/audio clips. - **Demo-driven conclusion**: closes with a live showcase of a personal project — "Gradient Bang, a multiplayer game that showcases real-time agent orchestration" — described as "built from the ground up with LLMs as the core of every interaction." - **Call to action tied to the company's event presence**: "We have a booth on the show floor. I'm online everywhere." - **Forward-leaning, opportunity-focused tone toward AI's impact**: frames VisiCalc as "a counter-argument to the argument or the fear or the concern that AI is going to lead to mass unemployment" (an argument made in the talk, not a private motive claim). ## Distinguishing Claims from Demonstrations - **Creator claims** (unverified within the material): Pipecat's market position, customer list, open-source status. - **Demonstrated patterns**: deep historical knowledge of HCI and computing, personal longevity in the field ("This long project... is still what I'm working on 15 years later"), and comfort presenting speculative future directions ("the next next thing") to an engineering audience. # Delivery Observation: Kwindla Kramer — "The New Primitives: Building AI Native Software" ## Overall Tone - **Warm, conversational, conference-keynote register.** Opens with direct audience address: "Good morning. I know a lot of you in this room. It's great to see you." - **Enthusiastic but grounded.** Repeated expressions of excitement tied to concrete topics: "I was as excited about HTML in 1995 as I am about agents today"; "I have a lot more things I'm super excited to talk about." - **Light, self-deprecating asides** that soften the historical sweep: "I went long after wrap-up, but I will say that the first version of this new draft talk was an hour." ## Recurring Phrases & Verbal Habits - **"Really" as an intensifier**, used repeatedly: - "a really great example" - "really amazing ways" - "it's really, really clearly influenced by As We May Think" - "in a bunch of really interesting and lovely ways" - **"So" as a discourse reset** to open transitions, appears many times: "So, what will we build?"; "So, how do we go from agents to agents plus plus…"; "So, the video shows…"; "So, the full 4-minute video is one take." - **"A lot of" as a quantity hedge/colloquialism**: "a lot of you in this room," "a lot of fun," "a lot of time writing HTML," "a lot of people building the web." - **Repeated analytic framing "the big job was…" / "the challenge was…"** when moving through decades: - "in the 1950s the big job was to figure out more effective ways of transmitting human intent" - "in the 1960s the challenge was to make these machines interactive" - "in the 1970s, computers had become powerful enough that the next big job was designing abstractions" - "in the first decade of the new millennium, the big job was to make all of this computing stuff mobile" ## Teaching / Structural Habits - **Historical timeline scaffolding.** The talk is organized as decade-by-decade progression (1945 → 1950s → 1960s → 1970s → 1980s → 1990s → 2000s → 2010s → now), explicitly announced: "I'm going to try to put all this in the context of the roughly 80-year history of digital computing so far." - **Embedded media clips as evidence.** Repeatedly pauses narration to play sourced clips (Satya Nadella podcast, Star Trek, Knowledge Navigator 1987, Minority Report, Iron Man, a demo reel, a Tavis video), then annotates them afterward: "So the gestural interface in Minority Report was implemented on screen as special effects, but it was actually based on John's PhD work at the MIT Media Lab." - **Explicit callbacks and forward references**: "and hold that thought cuz we're going to come back to it." He does return to Knowledge Navigator later. - **Analogy as the central teaching device.** The web-page-to-web-app analogy anchors the thesis: "just like we went from web pages to full-blown web and native mobile, clearly we're going to chart a path to a new fully AI native software." - **Coining shorthand labels** for conceptual compression: "I think of this is kind of agents plus plus"; "the next next thing." - **Recommendations to the audience**: "This is very much worth tracking down online and watching all of if you haven't seen it" (repeated for the Tavis video). ## Personal-Anecdote Integration - **First-person historical testimony** is a recurring credibility device: "I was a baby programmer in 1995"; "I co-founded a startup with John in 2006 to make the Minority Report interface into a commercial product." - **Personal investment framing**: "This long project to build the multi-modal, multi-device, multi-screen, multi-player, ubiquitously connected computer is still what I'm working on 15 years later." ## Vocabulary & Register - **Technical vocabulary delivered accessibly**: "harnesses," "context engineering," "progressive disclosure of tools," "asynchronous non-blocking context compression," "inference calls." - **Culturally fluent references**: Vannevar Bush's "As We May Think," Sketchpad, VisiCalc, HAL 9000, memex, Knowledge Navigator — used as recurring touchstones rather than one-off name-drops. - **Casual filler in an otherwise polished talk**: "cuz we're going to come back to it," "like multi-model harnesses," "like the American Kubrick dystopian tradition." - **Occasional stumbles and repairs**, consistent with live delivery: "Google Google Sheets or Microsoft Excel"; "a interpretation of Arthur C. Clarke's"; audible "[clears throat]" moments; "Oh, sorry" mid-demo. ## Uncertainty Notes - **Pacing claims** ("We're going to go fast") are stated by the speaker but the transcript cannot confirm actual pace, gesture, or slide usage. - **Repetition of "the big job was…"** is well-evidenced across four decades; the "So," and "really" patterns are also frequent enough to treat as stable habits. Single-instance items (e.g., "cuz") appear to be isolated colloquial moments. # Position Record: "The New Primitives: Building AI Native Software" — Kwindla Kramer, Daily ## Speaker & Context - **Speaker:** Kwindla Kramer, Daily (developer infrastructure for real-time audio, video, and AI; team behind **Pipecat**, described as open source, vendor-neutral, and "the most widely used framework for building voice agents today," used by AWS, Nvidia, Anthropic, and thousands of startups/enterprises). - **Venue:** Voice track, AI Engineer World's Fair. ## Central Thesis - We are at the beginning of an "intelligence age," analogous to the start of the computing age — a comparison Kramer draws to Vannevar Bush's 1945 essay *As We May Think*. - Current agent work will evolve beyond "agents" and "agents plus plus" into a **fully AI-native software** — analogous to the shift from web pages (1995) to web and native mobile applications. ## Historical Argument (Kramer's Timeline) Kramer modifies Bush's timeline with hindsight of 80 years of computing: - **1940s–50s:** First job was transmitting human intent to machines — first programming languages, first compilers; combining mathematical formalism with natural language. - **1960s:** Interactivity, two-way dialogue; Sketchpad; science fiction (Star Trek, HAL 9000) shaped popular imagination — "ideas matter." - **1970s:** Scaling abstractions — relational databases, declarative languages, Smalltalk and OOP. - **1980s:** Personal computer (Macintosh 1984, Windows 1.0 1985); Microsoft delivered "a computer on every desk and in every home." - **1990s:** Network/web. Kramer's claim: **the web was multimodal from the beginning**, anticipating that text, audio, video, and data belong together — in his view the single most important thing about the web. - **2000s:** Mobile, continually connected computing; on-screen futurism (*Minority Report*, *Iron Man*). - **2010s:** The cloud, laying groundwork for AI training/inference. - **Now:** Agents, and emerging "agents plus plus." ## Key Claims & Reasoning ### 1. Vannevar Bush's prescience - *As We May Think* predicts screen document display, OCR, speech-to-text, text-to-speech, programming languages, hypertext, search engines, data networks, Kindle-store-like devices, voice and brain interfaces — written "right at the very beginning of the computing age." ### 2. The web page → web app analogy - Kramer states he wrote HTML by hand, web servers in C, and Perl tooling in 1995, and was "as excited about HTML in 1995 as I am about agents today." - **Reasoning:** Just as web pages persisted but discourse moved to web/native applications, agent work will give way to a new AI-native software layer. ### 3. VisiCalc as counter-argument to AI-driven unemployment - VisiCalc "didn't put accountants out of business" — it expanded accounting-like work and enabled inconceivable new categories of work. - **Claim:** This is "potentially a counter-argument" to fears that AI causes mass unemployment. (Note: Kramer qualifies this as *potentially*, not a settled conclusion.) ### 4. Science fiction as design influence - *Star Trek* (1960s): optimistic talking computer; *2001*'s HAL 9000: dystopian counterpart. - Apple's 1987 **Knowledge Navigator** concept video "divides our timeline quite neatly in half" — presaging the AI agent era in a way Bush's Memex "didn't and maybe couldn't." - John Underkoffler's gestural interfaces (*Minority Report*, based on his MIT PhD work; *Iron Man*) are cited as "in a real sense... real technology." - Kramer personally co-founded a startup with Underkoffler in 2006 to commercialize the Minority Report interface; states this long project is "still what I'm working on 15 years later." ### 5. The present moment - Satya Nadella (quoted clip, No Priors / Latent Space crossover): products like GitHub Copilot are "multimodal harnesses with tools access" enabling "progressive disclosure of tools" that are "token efficient," fed with "rich context." - Kramer characterizes the trajectory as: last year's conference topics (loops, tool calls, context engineering) → "agents plus plus" (multi-modal harnesses, copilots embedded in all software, organization-level harnesses) → the next thing beyond agents. - The Tavis team's reimagined Knowledge Navigator video (played in the talk) is presented as evidence: "one take, completely real," familiar yet new. - We can now "build the Memex and Jarvis... and Knowledge Navigator... for real, completely working," and "by building those things, we'll figure out what we want to build next." ### 6. Demo: Gradient Bang - A massively multiplayer game Kramer is building with friends as "a canvas to really think about what AI native software can be." - **Claims:** LLMs at the core of every interaction; hundreds of inference calls per moment; "we couldn't have built anything like this even a year ago." - Demonstrated patterns: asynchronous non-blocking context compression, long-running shared-context sub-agents, progressive skills loading, dynamic UI generation, conversational voice. ## Qualifications & Unresolved Points (preserved as stated) - The VisiCalc unemployment counter-argument is explicitly **tentative** ("potentially"). - The path from agents to AI-native software is framed as projection: "clearly we're going to chart a path" — an expressed expectation, not an observed fact. - The "what will we build?" question is left open: Kramer proposes building the historical visions first, then figuring out "what we want to build next." - Kramer notes going "long after wrap-up" and that a first draft of the talk was an hour — signaling more positions exist beyond what was presented. ## Speaker Notes - Kwindla Kramer is also introduced by the transcript as "Quinn La Holman Cramer" — the transcript's rendering of his spoken name. - Attributions for quoted clips (Nadella, Star Trek, Knowledge Navigator, Minority Report, Iron Man, Tavis video, Gradient Bang) are as identified by Kramer within the talk; no independent verification is offered in the source. # Speaker Attribution Record — Video `01a15ca8-01d8-7999-b5c1-a6b0e760809e` ## Primary Speaker - **Quinn La Holman Cramer** (self-introduced as "Quinn La Holman Cramer"; title metadata: **Kwindla Kramer, Daily**) - **Role**: Presenter / keynote speaker at the **voice track, AI Engineer World's Fair** - **Affiliation**: **Daily** — "developer infrastructure for real-time audio, video, and AI"; team behind **Pipecat**, described as open source, vendor neutral, used by AWS, Nvidia, Anthropic, and thousands of startups/enterprises ## Embedded Quoted/Clipped Speakers (via played media, not present in room) - **Satya Nadella** (Microsoft CEO, per speaker's framing) — clip from a crossover episode of the **No Priors** and **Latent Space** podcasts discussing agent building and "multimodal harnesses" - **Star Trek** audio clip — unnamed computer voice and captain character (1960s science fiction example) - **Apple "Knowledge Navigator"** (1987 concept video) — unnamed assistant voice - **Minority Report** (2002) clip — unnamed film characters - **Iron Man** clip — unnamed AI assistant ("Jarvis"-style) voice - **Tavis team's reimagined Knowledge Navigator video** — unnamed assistant "Tom" addressing "Hassaan" - **Gradient Bang** game demo audio — unnamed game AI/narrator voices and player voice(s) ## Referenced Third-Party Works & Sources (per transcript) - **Vannevar Bush**, essay *"As We May Think"* (1945) — memex concept - **Ivan Sutherland's Sketchpad** (1960s graphical programming) - **Arthur C. Clarke / Stanley Kubrick**, *2001: A Space Odyssey* (HAL 9000) - **John Underkoffler** — gestural UI designs for *Minority Report* and *Iron Man*; speaker notes he **co-founded a startup with Underkoffler in 2006** - Historical products cited: VisiCalc, Macintosh (1984), Windows 1.0 (1985), Smalltalk, relational databases ## Speaker's Own Projects Disclosed - **Gradient Bang** — multiplayer game built with LLMs; described as "a project I've been working on with some friends" (personal/provenance note, not framed as a Daily product) ## Promotional Segments — Flagged - Opening self/company introduction: **Daily and Pipecat** promotion ("most widely used framework for building voice agents today") - Closing: invitation to **find the speaker** and visit **"a booth on the show floor"** — explicit promotional/lead-generation segment ## Third-Party Claims (attributed, not verified) - Pipecat usage claims ("most widely used," AWS/Nvidia/Anthropic adoption) — **speaker's own claim** - Nadella's characterization of Microsoft products as "multimodal harnesses" — **clipped speaker's claim** - Gradient Bang described as "entirely real" / "one take" — **Tavis team's claim relayed by speaker**; speaker claims "hundreds of inference calls" in the game ## Comment Availability - **No comment data supplied**; comment availability **unknown** from provided sources. \>\> Good morning. I know a lot of you in this room. It's great to see you. Welcome to the voice track at AI Engineer World's Fair. For those of you who don't know me, my name is Quinn La Holman Cramer. I work at a company called Daily. We make developer infrastructure for real-time audio, video, and AI. And we're the team behind Pipe Cat, which is the most widely used framework for building voice agents today. Pipe Cat is open source and vendor neutral. It's used by companies like AWS and Nvidia and Anthropic and thousands of startups and scale-ups and enterprises. And today I'm going to talk about what kind of agents we're building today, including voice agents, but not just voice agents, and what I'm interested in building next. And I'm going to try to put all this in the context of the roughly 80-year history of digital computing so far. So, we've got a lot to cover. We're going to go fast. But we're going to start in 1945 with an essay called As We May Think, written by an engineer, an academic, a civil servant named Vannevar Bush. Bush deeply understood technologies ranging from analog computers to photography to radio to radar. As We May Think is a extraordinary piece of writing. The essay predicts the development of, among other things, document display on a screen and document scanning and OCR and speech-to-text and text-to-speech and programming languages and hypertext and search engines and data networks. Something like the GoPro camera, something weirdly like the Amazon Kindle store, and voice interfaces and brain computer interfaces. And I've been thinking a lot about As We May Think lately because Bush wrote this essay right at the very beginning of the computing age. And I think it feels to most of us like we're working right at the beginning of a new age, the intelligence age. So, what will we build? Well, at the moment we're building agents and we're having a lot of fun doing it. And a lot of the AI engineering work we're all talking about this week is focused on building a full coherent software stack for AI agents. Here is Satya Nadella talking a couple weeks ago on a crossover episode of the No Priors and Latent Space Pod about the challenges of building agents in 2026. \>\> That's sort of \>\> That's right. So, so in some sense you kind of want to harness to define the models, the the data, uh and the tools. And so that you have a loop across those three. And so what we are trying to first of all make sure is each of our products that we build, right? Whether it's GitHub Copilot or the security copilot the stuff we showed with M dash or even the discovery for science, it doesn't matter. All of them are multimodal harnesses um with tools access so that you can do this progressive uh disclosure of tools even so that they're token efficient. Uh and then you're feeding it with very rich context. \>\> So, if you were here last year at AI Engineer World's Fair, you could draw a through line from the things we were talking about last year to loops and tool calls and context engineering and the stuff we're focused on this year to some emerging ideas. Uh you can hear that in Nadella's clip just there. I think of this is kind of agents plus plus, like multi-model harnesses and software copilot embedded in every single piece of software, organization level harnesses. So, how do we go from agents to agents plus plus to the next thing beyond agents. Well, the last time we had this kind of massive change in how we write software and what we write software for and to do was the early days of the World Wide Web. And I was around for the early days of the World Wide Web. I was a baby programmer in 1995 and the thing we talked about all the time in 1995, the way we talk about agents today, is web pages. I spent a lot of time writing HTML by hand and building web server software in C and indexing and search software in C and authoring tooling and management infrastructure for web pages in Pearl. I was as excited about HTML in 1995 as I am about agents today. And the web page is still with us and it's still important and useful. But today we talk a lot more about web applications and native mobile applications than we talk about web pages. So, just like we went from web pages to full-blown web and native mobile, clearly we're going to chart a path to a new fully AI native software that comes after agents and agents plus plus. So, let's keep going back in time to in order to think about this future. Here's a timeline Vannevar Bush lays out and as we may think, he talks about the abacus, which was both an immensely useful device for doing practical everyday mathematical calculations and also an incredibly important theoretical tool that led to ideas like numeric place value and the concept of zero. And Bush talks about the massive jump from the abacus to the state-of-the-art electromechanical keyboard calculating machines that he had in 1945. And then he posits that we're about or he is about to witness and help create an equally large leap to what he calls the arithmetical machine. And then he goes a step even further than that and he invents or designs in that essay a device he calls the memex. And we have a little bit of an advantage over over Bush in 1945. We've seen 80 years of computing play out. So, we can modify his timeline a little bit. We can go from the abacus to the stored program computer to 40 years later the personal computer and 40 years after that this AI agents era that we're all collectively helping to invent and create and bring into being. So, the question for me is what did we build to go from those very first digital computers in the 1940s to the personal computer in the 1980s? Well, in the 1950s the big job was to figure out more effective ways of transmitting human intent to these new computing machines. We built the first programming languages. We wrote the first compilers. And the the theoretical underpinnings here were figuring out how to combine the elegance of mathematical formalisms with something a little bit more like natural language. And then building on that in the 1960s the challenge was to make these machines interactive. Make these machines capable of a two-way dialogue with humans. The '60s also saw the birth of graphical programming with systems like Ivan Sutherland's Sketchpad. And the '60s were an amazing era for science fiction. Even though almost nobody had access to a computer the computer became a big part of the popular imagination. The idea of a computer really resonated with people and ideas matter. For example, here is the idea of the computer in Star Trek. \>\> Put her on record. \>\> Recording. \>\> Come. Captain's log supplemental. Engineering officer Scott informs warp engines Can be made operational and re-energized. \>\> Computed and recorded, dear. \>\> Computer, you will not address me in that manner. Computer. \>\> Computed, dear. \>\> I love the background sound of punch cards going through a punch card reader. So, like you know the computer is working even though it's talking to you about what it's actually computing. There were of course a bunch of other talking computers in in science fiction of the '60s and the next year after this, the Kubrick movie that was a interpretation of Arthur C. Clarke's 2001: A Space Odyssey had the HAL 9000 computer. This is a much, much more dystopian view of a talking computer than the Star Trek computers. And by the 1970s, computers had become powerful enough that the next big job was designing abstractions that could scale to much larger amounts of data and much more powerful computing substrates. We got relational databases, which introduced new theoretical underpinnings for data manipulation. And we got declarative languages, which leveraged those new theoretical insights. And programming languages in general continued to evolve in what to me at least are really amazing ways. We got Smalltalk and object-oriented programming in the '70s. And all of this set the stage for the personal computer in the 1980s. The Macintosh shipped in 1984. Windows 1.0 shipped in 1985. And Microsoft's mission statement was a computer on every desk and in every home. And incredibly, Microsoft delivered on that mission statement. And we got a computer on every desk and in every home because these new personal computers delivered real, amazing, tangible benefits. Take VisiCalc, for example, which was the first spreadsheet program. A truly new abstraction for doing computation, numerical computing, two-dimensional, interactive, so durable and so useful that probably most of us in this room use a direct descendant of VisiCalc regularly, Google Google Sheets or Microsoft Excel or whatever. Or put another way, this was a spreadsheet in 1957. And this was a spreadsheet in 1985. And I think a lot about VisiCalc these days too because I think VisiCalc is an example of how transformative new technologies can be in the way of delivering a capability that used to require a lot of specialized people and specialized knowledge and making it generally accessible. And I think VisiCalc is a potentially a counter-argument to the argument or the fear or the concern that AI is going to lead to mass unemployment. Because VisiCalc didn't put accountants out of business. Instead, it made much much much much more accounting-like work possible. And it made new categories of work possible that we couldn't even really conceive of when a spreadsheet or doing a screen's worth of calculations as we think about it today took a roomful of people. So if we were here in the Moscone Center in 1985 and these two interfaces, the Macintosh System 2 and Windows 1.0 were state of the art, what would we have said the world would look like in 10 or 20 or 30 or 40 years? Well, we actually have a really great example of a prediction from that time. Like as we may think another famous document in the history of human computer interaction, concept video from Apple made in 1987 called Knowledge Navigator. This is very much worth tracking down online and watching all of if you haven't seen it. I'm just going to play about 20 seconds from the middle. \>\> You have three messages. Your graduate research team in Guatemala, just checking in. Robert Jordan, a second semester junior, requesting a second extension on his term paper and your mother reminding you about your father's \>\> surprise birthday party next Sunday. \>\> So, the video shows a foldable tablet, a touchscreen interface, \[clears throat\] a conversational voice assistant with a really strong personality, access to both global and personal information, real-time video generation, real-time computer vision, seamless video call integration, delegation of complex tasks for autonomous execution, and what we might call today continual learning. And it's really, really clearly influenced by AS we may think, but it's also quite different. It really is updated for 40 years of progress, and it really does sort of presage this AI agent era we're in now in a way that Vannevar Bush's Memex didn't and maybe couldn't. The Knowledge Navigator video divides our timeline, I think, quite neatly in half, and hold that thought cuz we're going to come back to it. The 1990s were about the network, first local area networks and dial-up, and then the internet and the web, and with the benefit of hindsight, I now think that the single most important thing about the web was that it was multimodal from the very beginning. More even than the GUIs of the 1980s, the web anticipated that text and audio and video and data were not different things to be used in different programs, they belonged together. And in a real sense, the web was an attempt, and a conscious attempt on the part of a lot of people building the web to make that Knowledge Navigator video real. Then in the first decade of the new millennium, the big job was to make all of this computing stuff mobile and continually connected, to put this new multimodal networked computer in your pocket, literally, to give a supercomputer to everybody in the world that they could carry around in their hand. And as with the 1960s, there was an efflorescence of like futurism on screen in the first few years of the new millennium. And I think it was because computers you could carry around with you and cameras everywhere and a kind of Moore's law for pixels making screens super cheap really gave us a chance to think through what we thought the future would look like in a new way. A lot of stuff we could almost but not quite build was cohering in the minds of people working on these machines. And the best and most famous Hollywood computers from that era were created by John Underkoffler \[clears throat\] for the films Minority Report and Iron Man. Here's Minority Report from 2002. \>\> It's no longer there. \>\> Time frame? \>\> 13 minutes. \>\> Hey Chief, investigator from the Feds here. \>\> Yeah, I don't need some twink from the Fed poking around right now. \>\> John, I wrote it down on your calendar. I left you a message at your house. \>\> Check in with the Favors ahead of Ford and see if the neighbors knew where they went. Check all relations. \>\> Check the neighbors and relations. \>\> But John \>\> It's actually \>\> Just get him some coffee. Tell him some stories how I save \[music\] your ass every day and you can't do without me. \>\> I got coffee. Thank you. \>\> Danny Witwer. Twink from the Fed. Oops. Gone. \>\> So the gestural interface in Minority Report was implemented on screen as special effects, but it was actually based on John's PhD work at the MIT Media Lab. In a real sense, this was real technology. John had brought the UI out of the small screen and into the world with us in a bunch of really interesting and lovely ways. John also consulted on Iron Man, which is a very different view of the future than you Minority Report, which was Spielberg working in like the American Kubrick dystopian tradition. Iron Man is really squarely in that Star Trek goofy futurist tradition. But I think you could see the common elements in the UI depicted on screen. It's still from the same era. \>\> Wake up, Daddy Sean. \>\> Welcome home, sir. \[music\] Congratulations on the opening ceremonies. They were such a success. As was your summit hearing. \>\> \[music\] \>\> And may I say how refreshing it is to finally you in a video with your clothing on, sir. You! I swear to god, I'll dismantle you or short your motherboard. I'll turn you into a wine rack. \>\> I co-founded a startup with John in 2006 to make the Minority Report interface into a commercial product. This is our demo reel from 2012, 6 years into that work. \>\> \[music\] \>\> This long project to build the multi-modal, multi-device, multi-screen, multi-player, ubiquitously connected computer is still what I'm working on 15 years later. In 2010s, we built out the cloud, which laid the groundwork for the infrastructure and data centers and data capacity we would need to scale up AI training and inference, which brings us to now. We're building agents. And we're starting to think about agents plus plus. But I think we can also start to think about the next thing, the AI native software that is to agents what today's internet is to the web pages of 1995. And one way to think about the story is this. We went from the calculator to the computer to the personal computer to the global cloud computer. And now we actually have the ability to build the Memex and Jarvis from Iron Man and knowledge navigator from that 1987 video for real, completely working. And by building those things, we'll figure out what we want to build next. A couple of weeks ago the team at Tavis released a reimagined knowledge navigator video this time entirely built on real and available technology. I'll just play another 20 seconds of this, but like the original knowledge navigator video, this is worth tracking down and watching in full. \>\> Good evening, Hassaan. I adore that houndstooth jacket you're wearing today. Anything I can help with or would you like to review tomorrow's schedule? \>\> Thanks so much, Tom. Yeah, let's review tomorrow's schedule and see how busy it is. \>\> Opening your calendar now. Here is the quick version since it is late. Tomorrow morning is slammed. Investor meeting at 9:00, then back-to-back one-on-ones and internal meetings until 1:00. \>\> So, the full 4-minute video is one take, completely real. And when you watch it, it really does feel both like the knowledge navigator video from 1987, familiar but built on real technology, and like something brand new. And I'll just close with a massively multiplayer game project I've been working on with some friends as a canvas to really think about what AI native software can be. This game is built from the ground up with LLMs as the core of every interaction. At every moment in the game, there are hundreds of inference calls happening and we couldn't have built anything like this even a year ago. Oh, sorry. \>\> Welcome to Gradient Bang, a multiplayer game \[music\] that showcases real-time agent orchestration. Gradient Bang demonstrates several patterns for AI sub agents such as asynchronous non-blocking context compression. \>\> Okay, make a note for later. We are going to eliminate Heliotrope from existence. \>\> Noted. \>\> Long-running sub agents that share context. \[music\] \>\> Eagle is on five trade loops. Hawk and Raptor are on five exploration loops \[music\] each. Your fleet is busy. \>\> Progressive skills loading. \>\> How much does your average ship cost? \>\> Ships range quite \[music\] a bit, Captain. \>\> Dynamic user interface generation. \>\> Show my task history. \>\> Certainly. \>\> Uh hide the map. \>\> Okay. \>\> And conversational \[music\] voice. \>\> No, I don't want to exchange it. I just want to sell it for cold, hard cash, please. \>\> I'm afraid \[music\] the galaxy doesn't allow you to be shipless and hitchhike. \>\> So, I went long after wrap-up, but I will say that the first version of this new draft talk was an hour. So, I have a lot more things I'm super excited to talk about with all of you. So, if you are interested in this stuff, come find me. We have a booth on the show floor. I'm online everywhere and I'm excited to build agents cuz agents are awesome, but also to build the next next thing, too. Thank you. \>\> \[applause\] \>\> Mhm.