@no_stp_on_snek: one last thing: the real downside i found testing Ornith-1.0 (the new agentic coder): it over-gates legitimate work. on…

X AI KOLs Following Models

Summary

A tester reports that the new Ornith-1.0 agentic coder model over-gates legitimate work by demanding excessive prerequisites, a trade-off from its cautious training, while stock Qwen3.6 executes simple tasks directly.

one last thing: the real downside i found testing Ornith-1.0 (the new agentic coder): it over-gates legitimate work. on simple, fully-disclosed requests it would stall, demanding access or prerequisites instead of just doing the thing or delegating it. stock Qwen3.6 just executed. textbook agentic-RL artifact: trained to gather context and build scaffolding before acting, it over-applies that to tasks that should just get done. the same caution that makes it refuse a poisoned premise makes it over-ask on easy stuff. tradeoffs.
Original Article
View Cached Full Text

Cached at: 06/28/26, 03:55 AM

one last thing:

the real downside i found testing Ornith-1.0 (the new agentic coder): it over-gates legitimate work.

on simple, fully-disclosed requests it would stall, demanding access or prerequisites instead of just doing the thing or delegating it. stock Qwen3.6 just executed.

textbook agentic-RL artifact: trained to gather context and build scaffolding before acting, it over-applies that to tasks that should just get done. the same caution that makes it refuse a poisoned premise makes it over-ask on easy stuff. tradeoffs.

i have no doubts that some of the quirks can be fixed through more training, just end up playing whakamole sometimes. for a v1 pretty good.

Similar Articles