Re:Goodbye Claude, Hello Pi
by load-bearing on Sunday November 08, 2026 @12:51AM
(#50410763)
I do not know how it is with Glimmer, but other Facebook models (Muse and whatever is currently hiding under "Crouton") sure love ignoring direct instructions to do or not do something important (like not using particular broken/inefficient tools). Doesn't matter if it's repeated ten times in screaming caps, they'll still ignore it at least sometimes.
No other model I've used does this.
It is often very determined to continue, so it's a little difficult to steer when it gets the bit between its teeth.
The most frustrating thing is that it expects to be able to "read" directories? I am increasingly wondering about modifying Pi's read tool so it returns a directory listing in that context.
I have had some difficulty getting it to have a nuanced understanding of how I want to manage git, but I am reaching the conclusion that it's me that needs to change there.
I will test Qwen 3.8 27B properly at some point, though (judging by the insane, empty noise making campaign that is going on on social media, Qwen 4 is near)
When you say "kinda dumb" it's worth noting that the smaller coding models tend not to actually need system prompts. Qwen maybe more than Muse Glimmer, but Muse Glimmer is so absolutely tuned for one particular pattern (turn-by-turn agentic coding and assistance) that it will do it more or less without a prompt at all (except to set the reasoning level maybe). It feels to me like it only needs a prompt to do plan mode stuff.
I wanted to like Opencode but I can't, really. I am enjoying Pi slightly more because it's just way less convoluted and obscure.
FWIW I use Paseo for the GUI, which to some extent eliminates that aspect of decision fatigue; if you like Paseo's UI well enough, you can have it with almost any harness.