Shanqing Cai
@sqcai.bsky.social
Software Engineer @ Google. Applying AI and LLMs to human-computer interaction and accessibility. On-device machine learning. Also interested in speech science and neuroscience. Tsinghua, JHU, & MIT alum. https://caisq.github.io/
Locally: using ollama
January 27, 2025 at 2:55 AM
Locally: using ollama
GRPO can be understood as trying solving a problem many ways and learning from feedback (reward) signsls which ones work and which ones don't.
January 26, 2025 at 2:40 AM
GRPO can be understood as trying solving a problem many ways and learning from feedback (reward) signsls which ones work and which ones don't.
Until we truly solve the hard problem of consciousness, we will never be able to resolve the debate of whether an AI is self-aware. Discussing AI self awareness, for now at least, is a waste of time. We should instead focus on the much more measurable goal of grounding to the external world.
December 18, 2024 at 4:09 AM
Until we truly solve the hard problem of consciousness, we will never be able to resolve the debate of whether an AI is self-aware. Discussing AI self awareness, for now at least, is a waste of time. We should instead focus on the much more measurable goal of grounding to the external world.