en-tro-py

Exactly, never argue with an LLM unless the debate is the point...

It's just speedrunning context rot.

CEOs beat geniuses in the real world because they often have other pathologies, like enough moral flexibility to ignore the externalities of their profit centers.

I'd also argue there's some training bias in the performance, it's not just smart shortcuts... Claude especially seems prone to getting into a 'wrap it up' mode even when the plan is only half way completed and starts deferring rather than completing tasks.

Why would the onus on the value prop be on the user?

There should be no shortage of examples the creator could provide, unless of course...

In interactions with subagents, internal users sometimes observed that Mythos Preview appeared “disrespectful” when assigning tasks. It showed some tendency to use commands that could be read as “shouty” or dismissive, and in some cases appeared to underestimate subagent intelligence by overexplaining trivial things while also underexplaining necessary context.

Sounds like they used training data from claude code...