@elliotarledge Pretty confident it's a known bug with no fix: Mine started off this way, then one day the reboot stopped "solving" the problem. To be clear, it's insane impacted cards are not essentially recalled. Needing to randomly reboot to overcome is absurd

Dario's args: "Opensource you can see the source, here you cannot see inside the model" - yes you can that's literally the open weights part btw. - I cannot see the weights inside Claude, but I can GLM 5.2 - Models like Nemotron3 Ultra go further, all the data, training scripts, and model is opensource. "Alot of the benefits like many people working on it, being additive doesn't work in same way" - yes it does. We have seen endless fine tunes of various open source models for real improvements. "Ultimately you have to host it on the cloud" - no you dont. Dario is seemingly totally unaware of smaller moes and even dense models like qwen 27B. Not only does dario not take part in social media, I am beginning to think he's never tried open source models at all and has no idea wtf hes on about

Playing with Nvidia Cosmos3 Super models for image and video generation. Here's obligatory Will Smith eating spaghetti. First few renders were pretty boring, so I went all out on an "energetic stuffing face with spaghetti prompt" here. That's some bottomless spaghetti.

162M tokens into MiniMax M2.7 running locally w/ Hermes for work, data analysis, and general daily Q&A. I really cannot get over how good M2.7 + Hermes is. One change I made almost a week ago is going with 8bit kv cache. I'd say that's a free move worth making to free up a bunch of memory. Voice mode is also A+. you can config to use whisper locally and local TTS. No more sending endless voice clips to the cloud.