Share this
You can’t vibe code a chip. At least not yet. Fortunately there are other approaches to innovating on this layer of the AI tech stack. The team at MatX has been hard at work doing just that - now 100 team members strong and with an additional $500 Million raised in their Series B.
It’s been fun to watch Mike and Reiner make deliberate and aggressive progress since they left Google in 2022 to launch their company. We were honest in our pitch to be part of their first fundraise: you don’t need us to tell you anything about chips and we probably couldn’t answer your level of question anyway, but there are lots of things about company building that maybe we can be useful on. And hopefully every now and then we are!
As Reiner writes in their announcement blog post
Mike and I started MatX because we felt that the best chip for LLMs should be designed from first principles with a deep understanding of what LLMs need and how they will evolve. We are willing to give up on small-model performance, low-volume workloads, and even ease of programming to deliver on such a chip.
If this journey sounds like one you should be on too, they’re hiring.