Yeah, I think Fabraix is doing something really important here. Anthropic just showed us that the problem isn't what people think it is. They found that attackers don't try to hack the safety features head-on. Instead…
Yeah, I think Fabraix is doing something really important here. Anthropic just showed us that the problem isn't what people think it is. They found that attackers don't try to hack the safety features head-on. Instead…