Comment by pixelmelt
2 days ago
An alternative is that these patterns just increase the likelihood of the next thing it outputs being correct, thus are useful to insert during training as the first thing the model says before giving an answer
2 days ago
An alternative is that these patterns just increase the likelihood of the next thing it outputs being correct, thus are useful to insert during training as the first thing the model says before giving an answer
What's next, motivational speaking for LLMs?
I remember reading about speaking in an encouraging manner to agentic AI leading to better results, but I can’t seem to find a citation for this.
That's pathetic. Pleading comes next then. And after that most likely praying.