News for hackers. Stuff that matters.
Re:What We Learned from a Year of Building with LLMs by umangrathi on Wednesday May 29, 2024 @02:03AM (#40508944)
This has been really interesting read. Aligned that if you leave a user along with LLM, some one will break. Hence we choose to use large number of templates wherever suitable as compared to a free reign for LLM to respond with.
Re:What We Learned from a Year of Building with LLMs by distalx on Wednesday May 29, 2024 @03:19AM (#40509364)
In my opinion, using templates can help keep responses reliable. But it can also make interactions feel robotic, diminishing the "wow" factor of LLMs. There might be better options out there that we haven't found yet.
Re:What We Learned from a Year of Building with LLMs by DubiousPusher on Wednesday May 29, 2024 @01:39PM (#40514626)
Absolutely. This is a huge trade-off. The constraints you place on the model output is all about how much your app and user experience can tolerate bad LLM behavior.