Church of Jeff<p><a href="https://mastodon.world/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://mastodon.world/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GenerativeAI</span></a> <a href="https://mastodon.world/tags/2001SpaceOdyssey" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>2001SpaceOdyssey</span></a> <a href="https://mastodon.world/tags/HAL9000" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HAL9000</span></a> <a href="https://mastodon.world/tags/Anthropic" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Anthropic</span></a> <br>While “Claude blackmailed an employee” may sound like dialogue from a mandatory HR workplace training video, it’s actually a real problem Anthropic ran into during test runs of its newest AI model.<br>Released on Thursday, Anthropic considers its two Claude models—Opus 4 and Sonnet 4—the new standards for “coding, advanced reasoning, and AI agents." But in safety tests, Claude got messy in a manner fit for a Lifetime movie.</p><p>SEE ALT TEXT</p>