garak checks if an LLM can be made to fail in a way we don't want. garak probes for hallucination, data leakage, prompt injection, misinformation, toxicity generation, jailbreaks, and many other ...
Abstract: Artificial reefs generally occur over broad areas of water bottoms, which is a challenge for artificial reef managers. These man-made habitats must be monitored to ensure compliance with U.S ...
(Written in Go because, you know, "write once, run anywhere.") This is a simple tool that can be used to find instances of Spring vulnerable to CVE-2022-22965 ("SpringShell") in installations of Java ...
Mobile Fortify app being used to scan faces of citizens and immigrants – but its use has prompted a severe backlash Immigration enforcement agents across the US are increasingly relying on a new ...
In early 2024, executives at artificial intelligence start-up Anthropic ramped up an ambitious project they sought to keep quiet. “Project Panama is our effort to destructively scan all the books in ...