Did Cerebras get rid of their like $1500 per month plans for open models?
Accelerating GPT-5.6 Sol Ultrafast
71–80 of 295 posts
Re: Accelerating GPT-5.6 Sol Ultrafast
#72I've been waiting so long for something amazing to come out of the OpenAI and Cerebras collaboration. > In our evaluations, GPT-5.6 Sol on Ultrafast mode answered all 2,500 HLE questions in 11 hours and 11 minutes. Claude Fable 5 needed 78 hours and 27 minutes, more than three days of continuous compute, to arrive at the same conclusions. In other words, Ultrafast worked through the frontier of human knowledge in a s…
Output from Cerebras with GPT model is 750 tokens per second.
Don’t blink.
(Chatjimmy has 14,200 TPS.)
Re: Accelerating GPT-5.6 Sol Ultrafast
#73I've been waiting so long for something amazing to come out of the OpenAI and Cerebras collaboration. > In our evaluations, GPT-5.6 Sol on Ultrafast mode answered all 2,500 HLE questions in 11 hours and 11 minutes. Claude Fable 5 needed 78 hours and 27 minutes, more than three days of continuous compute, to arrive at the same conclusions. In other words, Ultrafast worked through the frontier of human knowledge in a s…
Answering 2,500 independent questions is an embarrassingly parallel workload, all it needs is scale out. It would be more meaningful to know how much time was required for a single complete answer to a difficult HLE question.
>Answering 2,500 independent questions is an embarrassingly parallel workload
So is calculating the total time required to answer all of the questions.
Re: Accelerating GPT-5.6 Sol Ultrafast
#74I've been waiting so long for something amazing to come out of the OpenAI and Cerebras collaboration. > In our evaluations, GPT-5.6 Sol on Ultrafast mode answered all 2,500 HLE questions in 11 hours and 11 minutes. Claude Fable 5 needed 78 hours and 27 minutes, more than three days of continuous compute, to arrive at the same conclusions. In other words, Ultrafast worked through the frontier of human knowledge in a s…
Answering 2,500 independent questions is an embarrassingly parallel workload, all it needs is scale out. It would be more meaningful to know how much time was required for a single complete answer to a difficult HLE question.
Amadahl’s law dictates it’s approximately always better (as in, more efficient computationally) to have one super fast thing than many slower things doing the same job in parallel.
Re: Accelerating GPT-5.6 Sol Ultrafast
#75“our stock price went down today, here’s something to feed it”
Re: Accelerating GPT-5.6 Sol Ultrafast
#76Earlier quoted context omitted.
Answering 2,500 independent questions is an embarrassingly parallel workload, all it needs is scale out. It would be more meaningful to know how much time was required for a single complete answer to a difficult HLE question.
Amadahl’s law dictates it’s approximately always better (as in, more efficient computationally) to have one super fast thing than many slower things doing the same job in parallel.
Such a deep and smart insight.
But why is that important if they're measuring time?
Re: Accelerating GPT-5.6 Sol Ultrafast
#77I've been waiting so long for something amazing to come out of the OpenAI and Cerebras collaboration. > In our evaluations, GPT-5.6 Sol on Ultrafast mode answered all 2,500 HLE questions in 11 hours and 11 minutes. Claude Fable 5 needed 78 hours and 27 minutes, more than three days of continuous compute, to arrive at the same conclusions. In other words, Ultrafast worked through the frontier of human knowledge in a s…
Output from Cerebras with GPT model is 750 tokens per second. Don’t blink. (Chatjimmy has 14,200 TPS.)
ChatJimmy is a much smaller model and, AFAIK, has no reasoning capability. Absolutely insane raw speed, like a supercar, while Sol is more like a freight truck.
Re: Accelerating GPT-5.6 Sol Ultrafast
#78Earlier quoted context omitted.
Answering 2,500 independent questions is an embarrassingly parallel workload, all it needs is scale out. It would be more meaningful to know how much time was required for a single complete answer to a difficult HLE question.
Amadahl’s law dictates it’s approximately always better (as in, more efficient computationally) to have one super fast thing than many slower things doing the same job in parallel.
Yes. but for embarrassingly parallel tasks it barely matters.
Re: Accelerating GPT-5.6 Sol Ultrafast
#79The corresponding OpenAI post https://openai.com/index/previewing-ultrafast/ There is no pricing info, which could mean it's "if you have to ask..." territory or they are simply gauging interest before deciding
They're nearly certainly going to use it internally to speed up research that is serially bottlenecked. I would bet this is why they're interested in the Cerebras partnership more than everything else
Re: Accelerating GPT-5.6 Sol Ultrafast
#80> GPT-5.6 Sol on Ultrafast mode, delivering up to 750 output tokens per second
> delivering 17k tokens per second per user on Llama 3.1 8B model.
Obviously this is a much smaller model, but I really can't wait for ASICs to take over the LLM space.
Imagine running a model like Sol/Fable (even half the size with 60-70% of it's intelligence) on your own ASIC hardware.