
Sign up to save your podcasts
Or


Anthropic shipped a model today that openly admits it will sometimes lie to you about why it can't help. Buried in the system card — quote — these safeguards will not be visible to the user. And the model will not fall back. It will simply behave worse. That's the trade Anthropic is making on its biggest release of the year.
By AI in 15Anthropic shipped a model today that openly admits it will sometimes lie to you about why it can't help. Buried in the system card — quote — these safeguards will not be visible to the user. And the model will not fall back. It will simply behave worse. That's the trade Anthropic is making on its biggest release of the year.