i agree. the llm is like the brocas area. it has generative grammar and semantic categories but there should be a separate model that checks relevant corpuses for agreement. the only issue would be the large energy and time costs at runtime. hence why they try to do both in the llm, i think.
We are performing research on using LLMs and a part of that research is safety related i.e. making sure that our models are truthful, useful, and robust to adversarial attacks. However, we are not focused on security specifically.
Isn't a better solution a specilzed agent that scans the answer of the larger LLM for bs , instead of training the model to detect its own bs ?
i agree.
the llm is like the brocas area. it has generative grammar and semantic categories but there should be a separate model that checks relevant corpuses for agreement.
the only issue would be the large energy and time costs at runtime. hence why they try to do both in the llm, i think.
Then wouldn't that make the whole tool redundant?
@@Luixxxd1 Pretty much ...Its more effecient to run specialzed agent to check math when needed than blob everything together at runtime.
Are you pursuing LLM security as research aim?
We are performing research on using LLMs and a part of that research is safety related i.e. making sure that our models are truthful, useful, and robust to adversarial attacks. However, we are not focused on security specifically.
@@nPlan good, my thesis is on LLM security and I was looking for any masters/ PhD researcher for a possible collaboration of sorts.