I though it was just me... My agents have been smoking all weekend.
roon@tszzl
I don’t think I love anything as much as language models love “smoke tests”
6:42 AM · Jun 15, 2026 · 1.2K Views
Academic Graham Neubig and SaferAI founder Siméon Campos joke about AI agents constantly running repetitive, minimal smoke tests
Campos noted that OpenAI's Codex exhibits the same behavior
19001.5K
Sentiment
Sentiment building, check back later.
Cluster Engagement
Posts from X
Most Activity
Most Activity
No ranked X posts are available for this story yet.