Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GLM-5.1: Towards Long-Horizon Tasks

z.ai

Post reply on HN
Print view View original

1–10 of 285 posts

Re: GLM-5.1: Towards Long-Horizon Tasks

#6

Post by smith7018 »

dang wrote: post #5

[stub for offtopicness] [[you guys, please don't post like this to HN - it will just irritate the community and get you flamed]]

Hmm, three spam comments posted within 9 minutes of each other. The accounts were created 15 minutes ago, 51 days ago, and 3 months ago.

Interesting.

Hopefully these aren't bots created by Z.AI because GLM doesn't need fake engagement.

Re: GLM-5.1: Towards Long-Horizon Tasks

#7

Post by dang »

smith7018 wrote: post #6
dang wrote: post #5

[stub for offtopicness] [[you guys, please don't post like this to HN - it will just irritate the community and get you flamed]]

Hmm, three spam comments posted within 9 minutes of each other. The accounts were created 15 minutes ago, 51 days ago, and 3 months ago. Interesting. Hopefully these aren't bots created by Z.AI because GLM doesn't need fake engagement.

These comments are probably either by friends of the OP or perhaps associated with the project somehow, which is against HN's rules but not the kind of attack we're mostly concerned with these days. Old-fashioned voting rings and booster comments aren't existential threats and actually bring up somewhat nostalgic feelings at the moment!

Thanks for watching out for the quality of HN...

Re: GLM-5.1: Towards Long-Horizon Tasks

#8

Post by bigyabai »

It's an okay model. My biggest issue using GLM 5.1 in OpenCode is that it loses coherency over longer contexts. When you crest 128k tokens, there's a high chance that the model will start spouting gibberish until you compact the history.

For short-term bugfixing and tweaks though, it does about what I'd expect from Sonnet for a pretty low price.

Re: GLM-5.1: Towards Long-Horizon Tasks

#9

Post by embedding-shape »

bigyabai wrote: post #8

It's an okay model. My biggest issue using GLM 5.1 in OpenCode is that it loses coherency over longer contexts. When you crest 128k tokens, there's a high chance that the model will start spouting gibberish until you compact the history. For short-term bugfixing and tweaks though, it does about what I'd expect from Sonnet for a pretty low price.

> It's an okay model. My biggest issue using GLM 5.1 in OpenCode is that it loses coherency over longer contexts

Since the entire purpose, focus and motivation of this model seems to have been "coherency over longer contexts", doesn't that issue makes it not an OK model? It's bad at the thing it's supposed to be good at, no?

Post reply on HN