Hacker News Reader

Sorry, you are correct - I modified my original post. I get frustrated every time there's a model release and 1 week later everyone is saying NERF! NERF! 99.9% of the time these people are wrong, but you are right that it's technically not 100% due to a few edge cases.

I am more skeptical about the compute provider claim - do you have any evidence of that?

View on HN

I noticed that a few weeks back 5.6 sol would regularly glitch out and start speeding random words or loop and then the next day it'd be fine

and there's sometimes just huge floods of complaints from people all of a sudden, which is pretty unlikely to be a coincidence

I've seen that looping and glitching behaviour in over-quantized (~Q4 or lower) local models like Llama and Qwen 3.x. Thus, it is likely that they quantize the model after release to save on compute costs (while giving a favourable result at launch). That quantization can result in changes to the model's behaviour (you are changing the weights) that could be interpreted as nerfing.

Reply on news.ycombinator.com