HackerTrans
TopNewTrendsCommentsPastAskShowJobs

matanyal

no profile record

comments

matanyal
·2 anni fa·discuss
Hey y'all, we have a discord now for more discussion and announcements: https://discord.com/invite/TQcy5EBdCP
matanyal
·2 anni fa·discuss
When you have a pile of hardware and silicon Intellectual Property, patents, etc, IMO it's pretty clever. However, I'm a Groq Engineer, and I'm mega-biased.
matanyal
·2 anni fa·discuss
We intend to be very competitive on cost, power, hardware, TCO, whatever it is. Custom-built silicon+hardware has the advantage in this space.
matanyal
·2 anni fa·discuss
Thanks! Feel free to join our discord for more announcements and demos! https://discord.com/invite/TQcy5EBdCP
matanyal
·2 anni fa·discuss
We are great for image embedding (and audio, with more to come!) There is no reason you should be forced to use graphics cards intended for gaming for any AI workload.
matanyal
·2 anni fa·discuss
Thanks!
matanyal
·2 anni fa·discuss
Groq Engineer here as well; we actually built our compiler to compile pytorch, TensorFlow, and Onnx natively, so a lot of the amazing work being done by y'all isn't building much of a moat. We got LLama2 working on our hardware in just a couple of days!
matanyal
·3 anni fa·discuss
https://groq.com/groq-sets-new-large-language-model-performa...
matanyal
·3 anni fa·discuss
More info about Groq: https://groq.com/lpu-inference-engine/
matanyal
·3 anni fa·discuss
[flagged]
matanyal
·3 anni fa·discuss
Reading is one thing, but think about stuff like website generation, searching for information in massive datasets, real-time audio chats that don't sound like the AI misheard everything with a pause, and stuff like that.
matanyal
·3 anni fa·discuss
It told me "Yeehaw Ridem Cowboy" was potentially problematic, which is news to me living out west.
matanyal
·3 anni fa·discuss
[flagged]