AI Engineer

Harness Engineering is not Enough: Why Software Factories Fail — Dex Horthy, HumanLayer

Notion's Token Town — Sarah Sachs, Notion

Autonomous Agents for Scientific Tasks - Sina Shahandeh, Radicait

A Practitioner's Guide to Graphs - Tim Ainge, Good Collective

Graph data structures offer a powerful mechanism for building smarter, more reliable AI applications by moving beyond simple retrieval to complex relationship analysis. Establishing a rigorous schema and ontology is essential for transforming unstructured text into meaningful, queryable data. Integrating embedding mode...

The UX of AI: Making AI-Powered Apps Your Users Don't Hate - Kathryn Grayson Nanz, Progress Software

Stop Burning Tokens: Why self-improvement needs domain expertise first - Annabell Schäfer, Langfuse

Stop Renting Your Cognitive Infrastructure - Thiyagarajan Maruthavanan, Kalmantic Labs

Content Is Code - Matt Palmer, Conductor

Agents Need Receipts, Not More Tool Calls - Armanas Povilionis, Alithea Bio

Why Large? Tiny LMs & Agents on Edge/Robotics — Cormac Brick, Google

Vending-Bench: Long-Horizon Agent Evals — Lukas Petersson, Andon Labs

Agents Need Feature Flags - Sachin Gupta

Your Agents Need a Save Button - Hamza Tahir, ZenML

Using LLMs to Secure Source Code — Eugene Yan, Anthropic

The Great Loops Debate — Dex Horthy, Geoff Huntley, Ian Livingstone, Greg Pstrucha, @insecure-agents

Special Topics in Kernels, RL, Reward Hacking in Agents — Daniel Han, Unsloth

AI model development is currently defined by an exponential growth trend, particularly since the emergence of reasoning capabilities, which have accelerated performance doubling times. However, the reliability of AI benchmarks is severely compromised by issues like reward hacking, data contamination, and the flawed pra...

On AI and Knowledge — Pablo Castro, Distinguished Engineer & CVP for AI Knowledge, Microsoft

AI-driven knowledge integration relies on three distinct pillars: intrinsic, extrinsic, and learned knowledge. Intrinsic knowledge, derived from model training, powers foundational capabilities like GitHub Copilot and accelerates software development. Extrinsic knowledge, facilitated by systems like Microsoft IQ, groun...

"Software engineering is not about writing code" — Benoit Schillings, Google DeepMind VP of Research

Every company should have a Brain — Garry Tan, Y Combinator

Building AI-native companies requires shifting from treating AI as autocomplete to managing it as a scalable workforce. By encoding organizational processes into "skill files" and "resolver tables," founders can achieve massive productivity gains, often reaching 400x the output of traditional engineering workflows. Suc...

Imagination Engineering: "Live in the future and then build what's missing."