OpenClaw feels like it's learning: it discovers capabilities, stitches tools together, builds solutions it wasn't explicitly taught. The reality is simpler — it's an LLM calling tools in a loop, powered by Pi, a minimal coding agent SDK. This talk is about what you can build once you understand that. Matthias Luebken walks through embedding Pi in a real product: a B2B sales pipeline where incoming RFP emails route to customer-specific agent sessions, CLIs expose CRM and ERP data in a form the agent can use ...

MLX is an array framework for Apple Silicon, essentially PyTorch for your Mac, and this is a tour of what it can run: real-time vision models that describe the world around you, sub-100ms text-to-speech, speech-to-speech pipelines, omni models that take image and audio together, and video generation from a text prompt on 16GB of VRAM. A recent breakthrough called Turbo Quant cuts KV cache by 4x and gets 1M context running fully on device. The community projects include a native voice app, a robot speaking i ...

[music] >> How's everyone doing. It's a full room. Look at this thing.>> [laughter] >> Um okay, let's get started. Um okay. So, here is our, you know, agent.You know, it's got the turn loop, it's got the LM loop. You know, this little example sort of works well enough running on your own machine, but what if we want to sort of deploy these two production backends and, you know, run them on our servers. So, what do we want them to do, right. When they run on our servers, we want them to do, you know, long-ru ...

All right, welcome. Thanks so much for coming today. Um, I'm here to talk a little bit about context windows and I'm really excited because I get to talk about something that my team and I have been building for honestly close to a year now, uh, which is RA agent Alex. Um, so I'm going to talk a little bit about some of the lessons we learned about context management and uh, escaping the context window.So who am I. I'm Salian. I am the head of product at Arise.I have a technical background. I started out in ...

One-shotting is seductive. One line of code for web search. One prompt to serve every user. One deploy and you're done. Granola shipped a chat feature into their meeting notes app and found out what comes after that. This talk is a product engineer's honest account of why the gap between "it works in the playground" and "it works in production" is so hard to close. Web search looks like a single tool call — until it blows up your context, bills you 10p per chat, and your provider ships an overnight update t ...

The "Her" moment has been promised so many times it's become a joke. Every new demo, every smooth-sounding voice agent gets called it. Neil Zeghidour, CEO of Gradium AI and one of the researchers behind Moshi — the first full-duplex voice model — uses this talk to be honest about where the gap actually is and why it keeps not closing. The core tension: cascaded systems (speech-to-text, LLM, text-to-speech) are practical and getting smarter, but they're architecturally incapable of feeling like a real conver ...

[music] >> And so really excited to talk to you about giving your chat agent a voice. Um and 2025 was the year of the chat agents. And I think you either like died a SAS or you became AI first by adding a chat agent to your app.And so lots of you probably saw this tweet which went viral where it was linear post hog SEO where they all went and added their home screen is now the chat interface. And I actually really agree with this. It's like that's the default way that you want to now be interacting with AI. ...

Hi, I'm Isaac Robinson. I'm the research lead at Roboflow and I'm here to talk to you today about how transformers finally ate vision. Uh So, I'm going to start off with a brief summary of the competition. Then we're going to go through an overview of the evolution of the transformer, why that ended up winning out, some consequences of that, and what's next. So, where we started, convolutional neural networks. I'm sure everyone here is aware of how these work, but just to summarize, they have excellent indu ...

FLUX started as an image model story, but this talk makes the larger ambition clear: visual intelligence, not just image generation. From FLUX.1 through Kontext, FLUX.2, and FLUX.2 Klein, Black Forest Labs has been pushing fast, open releases while building toward models that understand images, video, audio, actions, and eventually the physical world itself. Along the way, Stephen Batifol walks through the research behind that direction, including BFL's work on self-supervised multimodal training, real-time ...

Deploying an agent is only the start. In this workshop, Samuel Colvin shows how to improve agents after they are already live, using Pydantic AI and Logfire to change prompts, models, and other parameters in production without redeploying or restarting services. The session covers managed variables for live prompt and model updates, how to run evals and compare prompt variants against real datasets, and how GEPA can be used to evolve better prompts from production traces and feedback signals. If you're buil ...