Play video
Pydantic is all you need: Jason Liu
AI Engineer session on Pydantic is all you need: Jason Liu. It adds practical context for how teams are building and operating AI systems in production.
Research archive, page 59
Browse entries 1393–1416 of 1605. Return to the first page to search and filter the complete collection.
Play video
Play video
AI Engineering 201: The Rest of the Owl
AI Engineer session on AI Engineering 201: The Rest of the Owl. It adds practical context for how teams are building and operating AI systems in production.
Play video
What's New in Inference Engineering — Philip Kiely, Baseten
TurboQuant reached twenty million people in March, and the memory stock index dipped because everyone assumed the KV cache had just halved. Philip Kiely had published Inference Engineering weeks earlier and watched a technique he had not covered go viral. So his team did the math.
Play video
The Frontier AI Inference Cloud for Agents — Byung-Gon (Gon) Chun, FriendliAI
Byung-Gon Chun's team invented continuous batching, now standard across the industry, and the work that followed inspired one of the most widely used open source serving frameworks. So when he says agents have changed the economics of inference, he knows the tooling from the inside.
Play video
Two Bugs That Hid in Plain Sight: A vLLM Debugging Detective Story — Asaf Gardin & Yuval Belfer
Once in roughly a thousand prompts, the model returned gibberish. No crash, no warning, and high confidence, which made it an engineering problem, not a quality one. It happened only in vLLM, only under load, and only with Jamba, AI21's hybrid of attention and Mamba layers.
Play video
Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards — Filip Makraduli
An RMS norm layer does almost none of the arithmetic in a transformer, yet a single decode step can launch it around 33 times, and a GPU is fast at math and slow at everything else: starting work, moving data, waiting. That gap is what FlashNorm attacks.
Play video
Vertical Mobility: Inference from MVP to Trillion-Parameter Workloads — Sitanshu Gupta, CoreWeave
On an agentic request, somewhere between 80 and 90 percent of the input is identical to the request before it, and prefill is the most expensive thing an inference stack does.
Play video
Routing LLM Inference in Production: From Engine Signals to Policy — Qianru Lao & Lu Zhang, OpenAI
The routing weights inside OpenAI's inference load balancer used to come out of a feedback loop. Engines reported signals, a controller smoothed them into a score, compared it to the fleet average, and nudged each weight up or down.
Play video
Total Recall: Agent Memory and Harness Engineering — Ignacio Martinez, Oracle
Ignacio Martinez registered the domain for this workshop on the Saturday before he gave it, and then asked the room not to request the biggest machines on offer, because he was paying for everyone's GitHub Codespace out of his own pocket.
Play video
The Search Engine for the Agentic Web — Will Bryk, Exa
Exa never meant to sell an API. Somebody sent them a message on Twitter asking for programmatic access to their search engine, and the answer was no, because there was no API to give.
Play video
If we want them to do Knowledge Work, design them as Knowledge Agents — Benjamin Clavié, Mixedbread
An agent searching a contract for "30 days" has no way to know whether it has found a deadline, a grace period, or a retention rule, or wandered into a medication schedule entirely. Benjamin Clavié uses that to explain why coding agents turned out to be the easy case.
Play video
Where RL Will Take Search — Maximilian-David Rumpf, SID.ai
Somewhere between 30 and 50 percent of an agent's tokens get spent on searching, almost all of it up front, before any of the work you asked for. Maximilian David Rumpf treats that number as the whole opportunity.
Play video
"My name is... my name is...": A Linguistic Map for Voice Agents — Midam Kim, ServiceNow
Midam Kim spells her first name for a voice agent, letter by letter. The bot reads it back with an N on the end. She corrects it. The bot replies thank you for your correction, then says her name wrong anyway, because its pronunciation rules are English and her name is not.
Play video
Realtime Voice Agents with Frontier Intelligence — Bohan Li, EliseAI
A background agent quietly makes the tool call, then drops the result into the main model's context so the model believes it made the call itself. That sleight of hand is one of three tricks Bohan Li uses to run a voice agent on a slow, genuinely intelligent model without the caller noticing the wait.
Play video
Voice Agents Can Just Do Things — Charlie Guo, OpenAI
The Moviefone hotline was a speech to speech system. The GPS unit in your parents' car was an event to speech system.
Play video
Your Voice Agent is Just a Walkie Talkie — Neil Zeghidour, Gradium
On a phone call with someone close to you, as much as 20 percent of the time you are both talking at once. Every real time voice model shipping today is half duplex: it is either listening or speaking, never both. That gap is the whole argument of this talk.
Play video
I Monitored Crime Audio. Voice Agents Scare Me More. — Sumanyu Sharma, Hamming AI
Sumanyu Sharma showed up for a doctor's appointment a voice agent had told him was booked. He was not on the schedule, the front desk turned him away, and he lost two hours.
Play video
How We Solved Agent Building — Andrew Qu, Vercel
When Andrew Qu handed Vercel's internal data science agent to its first trusted users, the verdict came back that it was awful. It had been clearing thirty percent of his evals and he thought the team was cooking.
Play video
Tokens Should Have Jobs — Katelyn Lesse & Angela Jiang, Anthropic
Given the same fixed budget of roughly 600,000 tokens, an agent that did nothing but execute scored 76 on a bench of financial analysis tasks. An agent that spent part of that identical budget asking a second agent for advice scored 89. Same tokens, different jobs, better answer.
Play video
Every step you take, every call you make: the reliable agent stack — Giselle van Dongen, Restate
A research agent asks a human to approve its plan, then waits. The wait might last a month, spanning restarts and redeploys, and while it waits the function consumes no serverless execution time at all.
Play video
Agents Without Code: Skills, YAML, and Filesystems Replaced Python — Philipp Schmid, Google DeepMind
By the third version of the same agent, the source directory is gone. What remains is an AGENTS.md holding the system instruction and a small bash script that installs the GitHub CLI on first run. No tool definitions, no JSON schemas, no Python.
Play video
Harness Engineering: Building the Production Cage for Powerful Domain Agents — Mike Chambers, AWS
Mike Chambers puts a dictionary entry on screen: a harness is a set of straps and fastenings used to control an animal. Swap animal for model and the definition holds. His working version is subtraction. Take an agent, remove the model, and everything left over is the harness.
Play video
No Memory, No Harness: Why the Database Is the Last Line of Defense — Kay Malcolm, Oracle
Half of Kay Malcolm's team sits in Europe and half in the United States, so when the Netherlands side commits code at four in the morning her time, the Americans wake up to the code and none of the reasoning behind it. Git records what changed, not why anyone decided it.
Play video
Building ambitious software — Jonathan Kelley, Dioxus Labs & Cognition
The Dioxus team got excited, maxed out their coding agent subscriptions, and turned out tens of thousands of lines of Rust covering features they had wanted for years. Almost none of it cleared the bar for merging. Those lines sat in draft, and Jonathan Kelley says they are sitting there still.