Pinned
Andrew Feldman
1,468 posts
Andrew Feldman
@andrewdfeldman
- The Wall Street Journal is starting to see what we’ve seen at @cerebras for years. The “reticle limit” - the boundary that defines how large a chip can be - has become the ceiling for progress. It has kept chips the size of postage stamps for more than 20 years. Every new
00:00- We are just a little bit faster than@nvidia GPUs on Qwen 235B...18X faster. @cerebras inference is blazing fast...come build cool stuff on Cerebras inference
00:00 
00:00- On Friday, @cerebras withdrew our S-1. We didn’t explain why - that was a mistake. So I want to give you the full picture. On September 30, 2024, we filed an S-1 with the SEC to take Cerebras public. Over the course of the last year, it had grown stale. 2024 was a
- My wife worked in the ER for 25 years. She taught me the most important lesson about saying no as a CEO: The same moment looks very different depending on which side you’re on. When you visit the emergency room it’s a day you will remember your entire life. Everything about
- Speed is the killer feature in generative AI. Nobody wants to wait 30 seconds...Remember when the internet was slow, Netflix delivered DVD's in envelops through the US Mail. Once the internet got fast, they became a movie studio. Speed changes the landscape, creates
00:00 - Replying to @chamath @JonathanRoss321 and @GroqIncAccording to Open Router, @cerebras is more than twice as fast as @GroqInc. Find today's data here: openrouter.ai/meta-llama/lla…
- A side by side comparison of @OpenAI 's new GPT-120B model running on @Cerebras versus @Google 's fastest Gemini Flash model running in the @GoogleCloud....we are just a little bit faster. Build fast. Build on Cerebras.
00:00 - Earlier this week @nvidia shared its performance on @OpenAI 's gpt-oss-120B model running on DGX B200 ( 8 two die Blackwell chips). They asked @ArtificialAnlys analysis to do a special set up for them. They showed performance of 900 tokens per second for one user, and
- Today, @cerebras luanched Qwen3 Coder 480B. According to independent benchmark firm @ArtificialAnlys it is just a little bit faster than the @nvidia GPU based competition. Build fast, my friends.
