Play video
Building Reactive AI Apps: Matt Welsh
AI Engineer session on Building Reactive AI Apps: Matt Welsh. It adds practical context for how teams are building and operating AI systems in production.
Research archive, page 44
Browse entries 1033–1056 of 1123. Return to the first page to search and filter the complete collection.
Play video
Play video
The AI Evolution: Mario Rodriguez, GitHub
AI Engineer session on The AI Evolution: Mario Rodriguez, GitHub. It adds practical context for how teams are building and operating AI systems in production.
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.
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
Bringing agents onto the world wide web — Paul Klein IV, Browserbase
When OpenClaw shipped, people started buying Mac minis to run it from home, SSHing in and clearing captchas off a residential IP. Paul Klein IV points out he has yet to see a SOC 2 compliant Mac Mini setup at scale, and that this felt like a reasonable answer is itself the problem.
Play video
Computer-use models will agentify the web, not APIs — Dhruv Batra, Yutori
To learn what a US school district is buying, you file a Freedom of Information Act request. Someone scans the email you sent, puts the scan on Google Drive, and attaches the relevant PDFs. Dhruv Batra's question is whether anyone seriously expects that office to publish an MCP server.
Play video
Improving Agents is a Data Mining Problem — Vivek Trivedy, LangChain
Does your agent get dumber after the first compaction? After the second? You cannot read that off the code, only off the traces, and there are far too many to read yourself.
Play video
Adaption Labs: Gradient-Free Continual Learning — Sara Hooker, Adaption
Fewer than five thousand people in the world know how to train a frontier model at scale, by Sara Hooker's estimate, and that knowledge travels like an apprenticeship rather than a literature.
Play video
Bringing Continual Learning into Enterprises — Samuel Denton, Applied Compute
A Qwen thinking model was taking up to 80 turns to submit on SWE bench. Applied Compute wanted it wrapping up by turn 40 and got the submit tool call rate from 22% to 60% with test pass rate flat.
Play video
Designing Agents (The Floor Is the Frontier) — Ben Hylak, Raindrop
Build the thousand example eval suite everyone tells you to build, switch harnesses, and 80% of it stops meaning anything. Ben Hylak's complaint is that eval advice is still written for the chatbot era, back when you knew the answer to nearly every question a user would ask.
Play video
Agents, codebases, and teams — Aditya Khandelwal, Amazon AGI Lab
Leave agent adoption to individuals and the engineer shipping two PRs a day ends up reviewing the ten that the early adopter ships. They fall further behind, the code they are reading is worse, and they conclude the agents are the problem.
Play video
Lessons from Studying Every Memory System — Shlok Khemani, Independent
A profile ChatGPT keeps on Shlok Khemani says he travelled to Turkey in 2025. He never has. The memory came from conversations where he was choosing between Turkey and Thailand, he went to Thailand, and the profile kept both with overlapping dates.
Play video
LLM Knowledge Bases: a practical guide — Ben Holmes, Warp
Talking runs about 200 words a minute and typing does not, which is why Ben Holmes starts a knowledge base with voice dictation rather than with organization.
Play video
Memory Harnesses for Long-Running Research Agents — Stefania Druga, Sakana.ai
On a literature review task where every paper already fit inside the context window, adding a memory harness changed nothing: the same accuracy, at higher cost. That negative result is the most useful thing in Stefania Druga's experiment, because it marks the boundary.
Play video
Evolution of agentic surfaces — Gagan Bhat & Isabella Kai He, Anthropic
Sonnet 4.5 developed what Anthropic's Applied AI team came to call context anxiety: approaching its context window limit, it would wrap work up early and stop with room to spare. They built context resets into the harness to compensate.
Play video
Velocity Sickness: What Happens When Your Whole Team Gets 10x Faster — Matt Dailey, Ref.
A newsletter writer walked Matt Dailey through an agentic pipeline good enough to amplify their own voice instead of flattening it, then mentioned they were now effectively writing a book every week. Dailey asked whether the audience was reading a book every week. They were not.
Play video
Multiplayer agentic engineering — Arjun Singh, Superconductor
Superconductor left a meeting bot sitting in a Google Meet at their expo booth for four hours, just listening. Someone passing through said they wanted coding agents to have clear acceptance criteria before declaring work finished. Nobody filed a ticket.
Play video
Local Models: Trust, Control, Optimization — Carter Abdallah, NVIDIA
When Fable was pulled back and access to frontier systems stopped looking guaranteed, Lucas Atkins watched enterprises move to Chinese open models, not because they scored better but because availability could be counted on.
Play video
Codex, Behind the Harness — Dominik Kundel, OpenAI
Once GPT 5.3 Codex Spark started serving a thousand tokens per second on Cerebras, inference stopped being the bottleneck and the network became it.
Play video
MCP Apps: Extending the Frontier — Ido Salomon & Liad Yosef
Chat and coding assistants still hand you walls of text when a button, a chart, or a small interactive view would say it faster.
Play video
MCP Tasks (async): Why Aren't Any Agents Supporting Them? — Cornelia Davis, Temporal
You invoke a tool and expect an answer, but real work takes time, and over that time connections drop, networks blip, and processes crash.
Play video
fighting slop with slop — Vaibhav Gupta, Boundary
You cannot tell great engineers what to do, and you increasingly cannot tell what an agent did either, so Vaibhav Gupta's answer is to fight slop with slop.
Play video
Reinforcement Learning without Verifiable Rewards — Will Brown, Prime Intellect
Reinforcement learning has been easy to sell where the answer is checkable, like math or code, and Will Brown's talk is about everything else. Most valuable tasks have no clean verifier, so Prime Intellect's work is on how you build reward signal when there is no ground truth waiting.
Play video
Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It — Olive Song
In this conversation, Olive Song, who leads reinforcement learning at MiniMax, opens up the stack behind the company's open weight models and the infrastructure that serves them. Her starting point is a belief in open source: put the weights out, let builders optimize on them, and share the capability widely.