tag

Model Safety

Read mini classes on this topic together, starting with the latest lessons for context.

1

lessons

Tag guide

Model Safety

This tag gathers mini classes around one specific topic. Start with the newest post, then use categories and related reading for context.

Warm hand-drawn overhead scene of a person and small robot sorting papers at a wooden table, with crumpled red sheets by a tray on the left and neat cream and teal stacks behind a clear divider on the right.

Development & Tech

Writing "This Is False" Next to Bad Data Doesn't Stop AI From Believing It

Fine-tuning on documents that keep saying a claim is false can still teach the claim; models learn the negation mainly when it's inside the sentence. Store true/false status in fields or rewrite the data.

about 5 min read · 2026.05.29