undefined | Better HN

0 pointsSol-2y ago0 comments

I think the ReAct paper also popularized this approach: https://arxiv.org/abs/2210.03629

0 comments

Perhaps these papers are also just coincidence. This field is so new and this type of reasoned completion chaining seems like it was an inevitability. I imagine many other active gpt products that got started early hand rolled similar systems.

tholor2y ago

Haystack's agent is indeed using the approach suggested in the ReAct paper

j / k navigate · click thread line to collapse

0 pointsSol-2y ago0 comments

I think the ReAct paper also popularized this approach: https://arxiv.org/abs/2210.03629

0 comments

broast2y ago

tholor2y ago

Haystack's agent is indeed using the approach suggested in the ReAct paper

j / k navigate · click thread line to collapse