We're all training similarly large base++; near same data, just pricing it differently... with grok removing a few filters and maybe some safeguards? For that matter, many of the benchmarks are flawed and are just easily gamed and whatnot. iykyk.
Very cool and what an amazing way to learn so much beyond what you do in those years at university (at least in the engineering sense). I wish we had software and hardware open to be able to run custom setups whether its NVIDIA on x64 or Ampere/arm64 with MacOS.
Considering Musk's power and the shrinking moat of OpenAI you would think he would be create something better with government support - or as some new department.
It seemed to be some capacity issue with the CDNs. When I stopped and restarted the stream it worked again. Perhaps they do not use real time multi-cdn switching.