alt Hacker NewsMy impression is that when you allow the model to use internal thinking as opposed to asking it to output its thinking first, it's more likely to backtrack when I detects a flaw in its plan. Said otherwise: once producing user-facing output it seems to lock into an approach, for better or worse.
Replies
vorticalbox • today at 9:39 AM
true but thats not how we work. We see a problem, we make a plan and then we adjust the plan as we find the flaws.
trying to reason about all the ways it can go wrong after a point just stops one from starting the task. Which is exactly what I find with models.
Yeah, I think I'm seeing the same thing. I don't have all the answers, I just think it'd be a mistake to throw the baby out with the bath water on this model. It seems significantly better than the other dense models near the same size (Gemma 4, Muse Glimmer, etc...). Maybe harness changes, maybe fine tunes or LoRAs.