Browse entries 1081–1104 of 1127. Return to the first page to search and filter the complete collection.
Play video
Getting an AI agent to behave the way you want isn't just about writing better prompts. In real systems, behavior emerges from a loop: prompts, evals, iteration, and feedback. Small changes in any part of that loop can completely change outcomes.
Play video
An agent runs entirely on your phone, no cloud, and plays Space Invaders, perceiving the scene, predicting the aliens, and dodging bullets in a loop. Another solves the New York Times mini crossword with a constraint graph that backtracks when the fills stop fitting.
Play video
An agent hands a doctor a clean, confident fact: the patient has a penicillin allergy. But that fact was synthesized from three sources, an EHR record, a lab report, and something the patient typed into an intake chatbot, and by the time it reaches the doctor, which one it came from is gone.
Play video
In July 2025 Dex Horthy turned the lights off: an agent software factory where nobody read the code. It fell apart. An issue appeared that no amount of prompting could fix, the site was down, users were furious, and he was digging through a codebase he had stopped reading three months earlier.
Play video
A second refund on the same order. A payout sent to the support desk instead of the buyer. An order status of "probably shipped." These are the kinds of mistakes a probabilistic agent makes and a paragraph of instructions cannot reliably stop.
Play video
Your agent can reach your data and still get it wrong. Vector search hands it a slice, Text2SQL hands it another, and neither tells it what is actually relevant or how the pieces connect, so the answer comes back confident and wrong.
Play video
Feed it 67 videos from the 2022 World Cup and ask for the near misses, the shots that almost scored but did not, each with a reason, and it returns them. Ask it to track Messi across the entire corpus and describe the camera framing, and it finds the moment he slaloms past a sliding defender.
Play video
AI Engineer session on From Text to Vision to Voice Exploring Multimodality with Open AI: Romain Huet. It adds practical context for how teams are building and operating AI systems in production.
Play video
Got a massive idea but stuck in the "just talking about it" phase? This session cuts the fluff and dives straight into how to build and prototype at lightning speed using AI Studio Build and Antigravity for free.
Play video
Connecting a coding agent to multiple services often means facing a dozen OAuth consent screens, a dozen token lifecycles, and a dozen chances for something to break. Despite having Single Sign-On, users still find themselves signing in repeatedly.
Play video
Most of us are pair-programming with one agent and stopping there. There's a lot more on the table. This workshop is about going from one agent to many. We'll start with codebase setup, the foundational work that makes agents effective on their own.
Play video
Open models are getting smaller, faster, and far more capable. In this talk, Cassidy Hardin walks through the latest advances in the Gemma family, with a focus on Gemma 4 and what it enables for developers building on-device and open-weight AI systems.
Play video
Agentic engineering so far has been a solo story: one developer and a dozen agents moving at warp speed. But speed without thoughtful planning and team alignment is just wasting tokens.
Play video
The best MCP server is the one you didn't have to build. At Cloudflare we have a lot of products. Our REST OpenAPI spec is over 2.3 million tokens.
Play video
Minutes into a call to demo a search API rebuilt to answer in under a second, the system got blocked, badly, in front of the client.
Play video
Scheduling a meeting is not finding a shared slot on everyone's calendar. It is a constraint optimization over authority, priority, and urgency, and an expert sees that immediately where a very capable model does not. Yu Su uses examples like that one to separate two things the field keeps collapsing together.
Play video
Train a model directly on ten thousand financial reports and you can drive the loss to 0.00001. It knows the documents perfectly. Then you generate from it and it collapses. Jack Morris uses that failure to set up the real problem.
Play video
A frontier scale checkpoint is around 500 GB, so shipping one to a rollout fleet in another region takes minutes to hours and kills any hope of weight updates landing in seconds. Nan Jiang's claim is that you can send roughly 500 MB instead and have the rollout engine reconstruct a bitwise identical weights version.
Play video
A compromised release of litellm, a Python package pulling three and a half million downloads a day, sat live for three hours installing a credential harvester for API keys, SSH keys and crypto keys along with a backdoor for remote command execution.
Play video
Quantize a single number in a model and it gets 20% dumber. That finding, from the super weights paper, is why Daniel Han's claim is less absurd than it sounds: GLM 5.2 goes from 1.5 terabytes to 250 GB, 86% smaller, without being 86% dumber. Layers are wildly unequal.
Play video
In 1945 Vannevar Bush described document scanning, OCR, speech to text, hypertext, search engines, a head mounted camera, and voice interfaces, in a single essay, before any of it existed.
Play video
Run terminal bench on Opus and on Haiku and Opus scores about three times better at a tenth of the cost, even though Haiku is far cheaper per token.
Play video
*Note: Kenton has just released Cloudflare OS today: https://x.com/KentonVarda/status/2084990137180590572 This talk was recorded a month prior to launch.* Claude needed a strikethrough the slide app did not have, so it added one to the app.
Play video
Every time a model launches there is a gap between the benchmark numbers and what the thing can actually do, and Nick Heiner argues the existence of the word benchmaxxing is the tell.