Hacker News Reader

Comment by kingo55 | Hacker News Reader

Poolside Laguna was quite good too (if you look beyond some of the teething issues).

Had Deepseek V4 Flash 0731 not launched, their latest Laguna release was really intelligent at non-coding tasks and it would have been my go-to model for my local workloads.

View on HN

For me Laguna frequently slightly corrupted text then it would be unable to notice the difference and get stuck making the dumbest conclusions. Thinks like typoed directory or function names. It was a great model other than that, but I ended up just going back to Qwen3.6

Make sure you've got the latest updates - both Poolside and Unsloth updated about a week after release, and that you're running via llama.cpp (I've noticed on the same model and same command line arguments, ik_llama.cpp loses quality for me).

Also just in case you didn't see it, Laguna S 2.1 was having issues on MXPF4 but people on Q4 and Q6 couldn't repeat the problem.

I just downloaded the latest llama.cpp and poolside Q4 and within 10k tokens it corrupted "Use ~/p/kevincox.ca as a reference" into "kevinc.ai" and then starts doing stupid things because the directory "doesn't exist".

In previous testing the Q8 was better but still had the same problem frequently enough to be very difficult to use. I don't know if it is a runner bug or model bug but at least with llama.cpp this seems to always happen and I haven't seen an issue like this with any other model.

Wow that's weird. I have it running sometimes at least 8 hours straight on a single prompt and no weirdness.

Could it be something weird like you're hitting your compaction limit?

No compaction happened. (That is set near 256k.) It seems to really not like my domain but I've seen it for various things as well (especially high-entropy tokens). Dropping random characters or various things. I've tried various flash attention and context quantization settings but nothing seemed to resolve it completely.

Reply on news.ycombinator.com