underscored

@underscored

6 clips · 1 follower

Follow
Tag:quality-assuranceClear

The best use of Opus 5.5 may be as an adversarial reviewer for another model. Claire now has Codex and Opus review each other's work rather than using one to replace the other. This cross-model loop catches issues either model might miss alone, making the additional cost worthwhile when quality matters.

— Lenny Rachitsky
1w ago

This process, where reviewing examples changes your definition of good, is called criteria drift. For example, if we'd prompted the agent to look for this 'objection handling' failure up front when we gave it traces to check, the agent would have caught the error automatically. But we'd only know to add 'objection handling' to our criteria after seeing this trace ourselves.

2w ago

When Claire tests her own onboarding flow, she naturally follows the happy path. She fills out every required field, clicks 'next,' and never intentionally tries to break anything. Codex tested the flow as both a team and an individual, pushed on required-field edge cases, and immediately uncovered a blocking bug that had survived for months simply because Claire always completed the form correctly.

2mo ago

The global aviation industry would grind to a halt without them. All parts have to be certified and need a comprehensive maintenance history to retain value.

5mo ago

Underscored — save the words that stop you in your tracks.

Start saving quotes →