Earlier quoted context omitted.
“Understands intent well and hammers until it gets there. “ If there’s anything I learned over the past 12-18 months is that this is a recipe for disaster, except for throwaway stuff. I thought most senior engineers settled on the fact that steering a model yields much better results?
For some tasks, there is no amount of "steering" that will produce sensible code. The model needs to be sufficiently capable as a baseline; this is the "intent" that people are referring to with Fable.
Just last night Fable decided to get into a rabbit hole of debugging a database driver issue by packet sniffing the network traffic instead of just adding debug statements to the code. Definitely needed steering, and I don’t know many people whose first intuition would be to use pcap when they have a segfault.