Daily Brief

Factory started building fully autonomous coding agents in April 2023, two years before enterprises were ready. Matan Grinberg now says this is indistinguishable from being wrong. The Factory co-founder and CEO explains how the company survived its "journey in the desert," including the decision to hand nearly all of its revenue back to customers when the product wasn't making developers obsessed. Matan makes the contrarian technical case that a model-agnostic harness beats the model-and-harness co-design that labs like OpenAI and Anthropic favor, because exposing a harness to many models keep

Barr Yaron shares her perspective on the results and emerging state of AI engineering in 2026. Speaker: Barr Yaron — Partner, Amplify Partners Barr backs founders building the AI infrastructure and applications that will shape the future. Links: X: https://x.com/barrnanas LinkedIn: https://linkedin.com/in/barryaron Website: https://barrchives.com Timestamps 0:00 Introduction and Survey Context 2:26 The AI Engineering Workforce 3:21 Current Modalities and Adoption 5:34 Model Strategy: Closed vs. Open-Weight 8:20 Cost as an Engineering Constraint 9:36 The Rise of Agentic Workflows 11:57 Infr

If everyone woke up sick tomorrow, coding-agent usage would drop to near zero. Matan Grinberg of Factory on the shift from copilot mode to agent-native software development.

LLMs are great at writing code. So the question we kept asking was: can they write code that produces a video? We thought it would be easy. The reality was a year of trying. We started with massive prompts to get very mediocre output. We made it more agentic to iterate and improve its output. This worked okay but wasn't production-ready. Eventually we tried Remotion. It got us deterministic video, but the React framework kept boxing the agent in. The more guardrails we added, the safer and more boring the outputs got. When we utilized plain HTML, CSS, and JavaScript, the creativity came back t

Full episode: https://www.youtube.com/watch?v=QbdbAhaJoCQ Me on twitter: https://x.com/dwarkesh_sp

Claude is capable of long horizon tasks. In this talk, we'll share lessons learned about building agent harnesses for reliable and secure long-horizon work. This include decoupling the brain and hands, self-verification, self-learning, and design for evolving agent harnesses. ### Lance Martin Member of Technical Staff · Anthropic [X/Twitter](https://x.com/RLanceMartin) · [LinkedIn](https://www.linkedin.com/in/lance-martin-64a33b5) · [Website](https://rlancemartin.github.io) Member of technical staff at Anthropic. Working on the Claude Platform, including Claude Managed Agents and the claude

To automate opening a bank account, your agent needs to verify identity, so a team wires it to the DMV and a passport service and ships it. Then the next team builds the next agent and rediscovers, from scratch, where its data lives, across a hundred databases plus Snowflake, Databricks, and S3, whether it can trust the version, and whether it is even allowed to touch it. Every agent repeats that wiring, nothing updates when a source moves without a manual rewire, and no agent is smarter tomorrow than today. Emil Eifrem's fix is to make the agents thin and put the intelligence in a shared subs

Stephen Chin gave two copies of the same agent the same facts about his home network, one storing them as a vector database, the other as a graph. He asked both what was running end of life software exposed to the internet. The vector agent said it could not find specific details. The graph agent traced the connections and flagged his daughter's Minecraft server running an out of date OS, then found real open management ports he quietly patched after the demo. Same data, and only one of them could actually answer. That gap is the whole talk. Most assistants, OpenClaw included, keep their memo

Not everyone needs the same tokens. Matan Grinberg of Factory on routing work across frontier models, Gemini Flash, and fine-tuned COBOL models — with policies written in natural language.

Yohei Nakajima was running a 500 question eval when his API key died at question 350. Normally that means restarting the whole long agent from scratch. Instead it rolled back one step and resumed at 353, because in ActiveGraph the log is the agent. Most people build agents around the LLM and bolt on memory and logging; Nakajima, the creator of BabyAGI, flips it and builds around an immutable event log. Every action and every change to the agent flattens into one typed log, which projects a graph that is the agent's state, so you get replays, rollbacks, and forks for free. On top of the log si

Can a model predict how a cell responds to a genetic perturbation it has never seen? Xaira Therapeutics' new virtual-cell model, X-Cell, is a 4.9-billion-parameter diffusion language model trained on X-Atlas/Pisces — the largest genome-wide CRISPRi Perturb-seq dataset ever built, spanning 25.6 million single cells across 16 biological contexts. Bo Wang (Chief AI Scientist) and Ci Chu (Chief Discovery Officer) explain why observational atlases can describe biology but can't predict what happens when you intervene, why they abandoned autoregression for a diffusion "editing" approach, and how a m

From spending $12 million building language models for code before the world cared to creating a Model Factory that can take a model from pre-training to release in eight weeks, Eiso Kant has spent more than a decade betting that code is the path to AGI. In this episode, the Poolside co-founder joins swyx and Vibhu to explain why ChatGPT felt like vindication, why Poolside embraced open weights and open research, and why he would rather live in a world with 100 foundation model companies than five even if Poolside were one of the five. We go deep on Poolside’s Model Factory: the engineering s