In 2018 I hand-wrote a C++ deep learning framework so I'd never pad a batch. In 2023 LLM serving landed on the same structure.

I tested 10 prompt-injection detectors on 629 real AI agent attacks. The best caught about half. Here's why, and the small tool I built instead.

We keep treating bad structure as an intelligence problem. Before adding another agent, ask whether a better tool, a clearer state, or a fixed workflow makes the agent unnecessary.

Here is a conversation that happens in a lot of companies right now: Dana: @assistant please close...

On June 14 I shipped a resolver with a green test suite. On September 1 I published a post about it....

Last week I opened an issue on laya, an open-source decision model with a little over 20k stars. The...

AI Harness Engineering · Essay Seven · derek wang (derekwang85) Dwight Eisenhower said it in a...

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content I...

Puedes darle a un agente de IA serverless una memoria durable y basada en significado usando búsqueda...

FraudLens: building a fraud investigator on TigerGraph, not a fraud classifier By Team...

Jev vs LLMs: Why AI Agents May Need a Decision Layer Here's an uncomfortable pattern in...