zlacker

[parent] [thread] 2 comments
1. hlfshe+(OP)[view] [source] 2025-06-24 16:48:56
The generally accepted term for the research around this in robotics is Constitutional AI (https://arxiv.org/abs/2212.08073) and has been cited/experimented with in several robotics VLAs.
replies(1): >>JumpCr+dB
2. JumpCr+dB[view] [source] 2025-06-24 20:07:58
>>hlfshe+(OP)
Is there any evidence we have the technical ability to put such ambiguous guardrails on LLMs?
replies(1): >>hlfshe+8Jk
◧◩
3. hlfshe+8Jk[view] [source] [discussion] 2025-07-02 19:31:17
>>JumpCr+dB
No. We can add guardrails, but nothing that has been proven to work reliably.
[go to top]