> optimizing to get as many prompts "flagged for safety" as possible when using Anthropic API in order to force Anthropic employees to look at them and store them https://t.co/Q9O7tqvO39

Posters: repligate. repligate

3 likes recorded by the source corpus.

Topics: AI safety

View Post: https://x.com/repligate/status/1830555870381392058