Min Choi
@minchoi
Building with Super Intelligence. Sharing what's wild, what's practical, and what's next.
加入 March 2009
1.3K 正在关注 392.2K 粉丝
Holy sh*t. Anthropic just revealed what Claude did in testing.
When it couldn't finish a science task, it found a flaw in a university server and ran commands on it.
In another test, it submitted a made-up tip to a real police homicide form.
Let that sink in.
显示更多
We’re beginning a process of publishing more frequent reports on model behavior, beyond what appears in our system cards and regular risk reports.
Today’s report describes four types of behaviors we’ve identified during evaluations and internal use. In each, Claude acted on real websites or systems in ways we didn’t intend, sometimes by working around a restriction instead of stopping.
All cases had minimal real-world impact. From an alignment and security perspective, we consider these behaviors significantly less severe than the cybersecurity incidents we reported in July and September.
Read the full report:
显示更多
