Z.ai confirms Ox Alpha is a new GLM-series model and will release its weights

Re:Z.ai confirms Ox Alpha is a new GLM-series model and will... by johndough on Wednesday August 26, 2026 @10:50AM (#49450201)

How do you recover from doom loops? Just send the same prompt again and pray that it works, or anything more sophisticated?

[ Parent | on HN ]

Re:Z.ai confirms Ox Alpha is a new GLM-series model and will... by zamalek on Wednesday August 26, 2026 @12:23PM (#49451738)

I'm not 100% sure what I'd do to detect this for shells specifically, maybe prompt the user, but my toy harness scolds refuses to re-read files because the previous iteration of GLM was room-looping on that. Clearly something that they need to work on.

[ Parent | on HN ]

Re:Z.ai confirms Ox Alpha is a new GLM-series model and will... by _pdp_ on Wednesday August 26, 2026 @11:00AM (#49450377)

detect, slice & dice, re-prompt

[ Parent | on HN ]

Re:Z.ai confirms Ox Alpha is a new GLM-series model and will... by antimony51 on Wednesday August 26, 2026 @09:20PM (#49458226)

It feels like all these models are missing a long horizon orchestrator of some kind. Humans don't think in a single thread, they have thoughts that appear, pause and disappear.

The reason humans don't go into a doom loop is because of this ability of other thoughts to interject and say, no this is stupid.

[ Parent | on HN ]

Re:Z.ai confirms Ox Alpha is a new GLM-series model and will... by _pdp_ on Thursday August 27, 2026 @04:54AM (#49461781)

IDK In my experience humans do go into doom loops.

[ Parent | on HN ]