9 Comments
User's avatar
Hector's avatar

Great read thanks for sharing!

RESTLESS BRAIN's avatar

Find a time to try it. Ir is extremely good and fascinating

mfsmillie's avatar

curious as to the quality of the responses (output). If I have 10 or 50 or 1000 or ALL agents (just asking an LLM) aren't we just converging towards the mean of all possible answers/responses and outcomes? Please explain the value here.

RESTLESS BRAIN's avatar

The thing is, the number of segments is auto-generated by the system. It depends, as I understand it, on data quality and the projected longevity of the report needed for the future. First experiment, described here, spawned 76 and burnt 24M, second — 123 and 57M. I can't say the results are so different. But the fields of study are competently different.

Dimitry's avatar

just WOW as always!

RESTLESS BRAIN's avatar

Thanks! You should try this. But be careful with tokens ;)

Dimitry's avatar

Now I'm on combining EURISKO with LLM with all my free time ;)