alt Hacker NewsNot super impressed with this considering you can get better results in seconds from any basic LLM workflow.
Replies
FloorEgg • today at 3:37 AM
Yes but for probably 1000x the energy/cost.
Not super impressed with this considering you can get better results in seconds from any basic LLM workflow.
Yes but for probably 1000x the energy/cost.
I wanted to know it was only returning source. My suspicions always go up when I have the LLM lean on its "deep memories". too much fluff, inconsistent translations, stuff like that.