Browse entries 1489–1512 of 1531. Return to the first page to search and filter the complete collection.
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
A customer replied good morning to an outreach text and the model called him immediately. Another confirmed a Thursday appointment, said sounds good, and was told a call was happening right now.
Play video
Roughly 70% of medical communication still moves by fax. What reaches Anterior is scanned fax bundles that can run past 300 pages, carrying handwriting, checkboxes, tables and images across one patient's entire clinical trajectory. Anuj Iravane calls it an observation through a fuzzy lens over a lifespan.
Play video
The springs in the middle of the loveseat in Clay Cockrell's counseling office gave out years ago, so gravity now tips a couple toward each other however hard they grip the arms. He kept it. The harder argument arrives with two numbers.
Play video
Uber could not exist without GPS. Ahmed Ahres uses that to argue real time is a change of medium rather than a speedup: before GPS you consulted a map somebody else had already made, and afterwards your own position became something you could act on continuously. He runs the same argument through film.
Play video
Someone in the audience asked the guitar what reality is, and the guitar answered.
Play video
Ten dollars now buys roughly three hours of continuously generated video, and fifty buys fifteen. Keegan McCallum sets that against the room's own habits, since plenty of hands went up for burning that much on coding tokens inside a single hour.
Play video
Asked how many in the room had ever received a proactive call from their healthcare provider, almost no hands went up. Vivek Muppalla treats that as the signature of scarcity: too few clinicians and too few hours, so the system triages and only the sickest get called.
Play video
Clinicians call it pajama time: the roughly two hours a day spent writing visit notes after work has finished. Abridge started there, and within two to three years the documentation product alone reached 300 of the largest health systems in the United States.
Play video
The most reliable way to render a person is to render the most boring average person and put them in the center of the frame. Sangwu Lee offers that as the price the big image models pay for consistency: ask a production model for a burning skull and every output comes back clean, competent, and nearly identical.
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.
Play video
Ross Taylor opens with some history: back in 2022 he worked on Galactica, an early large model for science that briefly crossed the Rubicon on curated high quality data and intermediate reasoning tokens before the reaction overshadowed the work.
Play video
Swap compute for data on the scaling curve and the same money buys a better model, which is why Ari Morcos calls data quality the compute multiplier and the most underinvested part of training.
Play video
The next step after a model ships is teaching it to keep learning on the job, and Raymond Feng lays out how Applied Compute trains custom models with reinforcement learning that plug into whatever harness an enterprise already runs.