| ▲ | iqihs 11 hours ago | |
Not super impressed with this considering you can get better results in seconds from any basic LLM workflow. | ||
| ▲ | jacksonastone 10 hours ago | parent | next [-] | |
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. | ||
| ▲ | FloorEgg 10 hours ago | parent | prev [-] | |
Yes but for probably 1000x the energy/cost. | ||