mutant
Joined 15 years ago
Joined 15 years ago
This could be generic to any harness, and ypubbuild all this.... Cruft.. around it.
an agent will frame any tool experience based on the user, not the tool. if the user has tight reigns on an agent that agent will infer experience different than a human running a harness in yolo.
agents reviews anthropomorphizes an llm, change reviews to experiences, then also gove context on the experience and you have a workable narrative. "review" requires insight an llm is utterly unsuited to provide. any agent "review" is tainted by the env.
or whatever. wtf do i know.
just not sure i trust the site's motives. the amarture website says in the hero "be the tool ** chooses" if you mean "code your tool to what users want" thats still the same as gaming benchmarks. what happens when an actor skews features reviews to something they are good at? i just don't see how this ends well
Why bother posting