Intel / video

fighting slop with slop — Vaibhav Gupta, Boundary

Source: youtube.com
Author: AI Engineer
Date: Published Jul 31, 2026

Context

The BAML programming-language team's approach to AI-written code moves review toward design, architecture and observed behavior. In Vaibhav Gupta's account, the team requires people to read design documents, records durable architectural constraints and uses automated checks to detect unwanted dependencies.

Agents also generate BAML programs and inspect execution records for problems. Humans help determine which reported issues are real before fixes proceed. The account describes several ways to examine a system without reading every generated line: agree on its design, enforce structural rules and investigate what happens when it runs.

Terms in this piece · Glossary

LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

Key quotes

“Slop is just any code you don't read.”
Vaibhav

“And we have a very simple rule in our team. Code can be slop, writing cannot.”
Vaibhav

“Our processes have to evolve if we're going to ship at agent speed.”
Vaibhav

“this is the least amount of slop your codebase will ever have to this day. So, just embrace it and start fighting it back.”
Vaibhav

“I think we do need a new Git. I think we do need a new database, and yes, I think we need a new programming language.”
Vaibhav

Read the source www.youtube.com