Re:Grok 4.6
by stingraycharles on Thursday August 13, 2026 @02:54AM
(#49282545)
That’s not how training pipelines work, and would be extremely wasteful for the biggest cost center as well.
[ Parent
| on HN ]
How about expanding a little instead of just saying "that's not how training pipelines work".
Re:Grok 4.6
by vorticalbox on Thursday August 13, 2026 @07:55AM
(#49284651)
pretty sure at this point no one is retraining from zero they have their big model and they fine tune it.
different training makes a different version (agent, info sec etc).
The GPT-5.5 and 5.6 Spud pretrain is a fresh pretrain run.
OpenAI has the Doug/Astro pretrain coming up next.
I was under the impression labs released post-training checkpoints fairly often?
So Model N/N+1 might literally have had the exact the same pretraining run and only differ on how much/what kind of postraining they got