Thread

1. Gareth321 · 1790064431 · focus · HN ↗

   OpenAI usage limits have been severely cut, and intelligence appears to be markedly declining, so I'm going to start trying these Chinese models seriously now. I don't mind if it takes longer. I just need the intelligence to predictably work the same way from day to day.

   1. loloisi · 1790074308 · focus · HN ↗

      Sol 5.6 xhigh had been a very reliable workhorse for coding for me via the 200 bucks sub.

      But this week they seem to have tweaked the system to a point at which all models (Astra, Sol, Luna) hit rate limits all_the_time without me being anywhere close to the weekly limit.

      Early results with MiMo 2.6pro are quite encouraging for anything that's non-UI work so likely switching spend for the time being

      1. cyanydeez · 1790165649 · focus · HN ↗

         having discussed this with people and saw similar discussion, it seems what they're doing is limiting long running context _and_ tweaking the models to run agents which basically strip mine your usage tokens because they want to avoid users taking up precious KV cache & VRAM space.

         So whatever they advertise as the context window, assume the model has been tweaked to keep it a quarter. Other commentors think all models are generally useless past 250k, and that might just be a reality of thesemodels.

         Eitherway: they're enshittifying precisely according to hardware vs users vs actual cash on hand, and smaller agents with less cache/vram on hand makes the overall hardware more performant.

         This of course is ignoring whether they're trying to stealthly deploy quantized models to eek out even more space on the hardware.

         This stuff is easy to learn when you play with local models.

Unofficial Hacker News client; not affiliated with Y Combinator.