Fireside Alpha
@firesidealpha
OpenAI Codex's Ro Varma says Cerebras blows up the speed-vs-cost curve that caps every other fast model, and you can achieve 10x speed in an economically viable way
"Fast mode is a little bit different because, basically by using more capacity, we can effectively serve the model
"Fast mode is a little bit different because, basically by using more capacity, we can effectively serve the model
1:00Fireside Alpha@firesidealpha · Jul 28OpenAI researcher Jeffrey Wang reveals the internal models running on Cerebras chips are so fast that tasks now finish before he even has the opportunity to context-switch, and it increases his productivity.
"Internally, we have some OpenAI models that are on Cerebras chips.
"Internally, we have some OpenAI models that are on Cerebras chips.
0:32 1 26