(no title)
IAmNotACellist | 7 months ago
You could train an LLM to consider the context potentially adversarial or irrelevant, and this phenomenon would go away, at the expense of the LLM sometimes considering real context to be irrelevant.
To me, this observation sounds as trite as: "randomly pressing a button while inputting a formula on your graphing calculator will occasionally make the graph look crazy." Well, yeah, you're misusing the tool.
devmor|7 months ago
It seems to me that solving this problem is one approach to removing the need for "prompt engineering" and creating models that can better interpret prompts from people.
Remember that what they're trying to create here isn't a graphing calculator - they want something conversationally indistinguishable from a human.
nomel|7 months ago
But, I would claim it’s a problem for a common use case if LLM of “here’s my all my code, add this feature and fix this”. How much of that code is irrelevant to the problem? Probably most of it.