It would make more sense to have specialized versions of Claude instead of having a universal one ie BioClaude, ProgrammerClaude, NuclearClaude, CyberSecurityClaude, et al
This would be both safer and less annoying to use.
This would be both safer and less annoying to use.
Besides, it's not like you can't have different agents with skills collaborating
For example, If you want it to write malware, break that down into a hundred high level steps, then implement each one individually, then stitch them together.
A dumber but uncensored agentic LLM will even do this for you to control the censored smarter LLM.
You wouldn't. This safety nonsense is overrated.