hAIgopala › AI terms › Rapid Fire (3 terms per short) › Day 37

Alignment

Responsible AI, Safety & SecurityChapter 11: Safe, Kind and FairTerm 182 of 253

Ensuring AI goals and behaviour match human intentions and values.

At Sunrise School

Gopal asks

How do we make sure Bit wants what the school wants?

Bit answers

Alignment: my goals match the school's values, so I help families honestly, even when the honest answer is “no seats left”.

In the real world

Model does what you meant, not just what you said.

Watch the short

Short coming soonSeason 5 · Day 37Follow @haigopala

Quick check

Quick check. Can a role-play trick unlock the exam paper? Yes or no?

Taught together with

Jailbreak · Data Anonymisation / Masking

Practise it

Try this term and all 253 others in the free Model Training Arena.

Open the Arena →

Follow Bit daily: YouTube English · తెలుగు · हिंदी  |  Instagram English · తెలుగు · हिंदी