|
|
|
|
|
|
by Ozzie_osman
1116 days ago
|
|
|
I know a big part of the discussion around this link is around whether AutoGPT is viable or not, but I think a more interesting piece are the papers linked at the bottom (especially the "Tool Maker" one). This pattern of "well, maybe the LLM can do that too" is just so obvious but so meta and simultaneously brittle. "LLM can use tools" -> "The tools can, themselves, be LLM-based" -> "The LLM can create it's own tools that it then uses". It's really turtles all the way down. |
|
|