Advice to Tenstorrent
github.com
Advice to Tenstorrent
1–10 of 67 posts
Re: Advice to Tenstorrent
#2With all due respect Mr. Geohot, you've got an awful lotta nerve to throw stones from your glass house. This guy needs to drop the middle school tough-guy tone and post numbers. The central thesis of this article is sound, lead with it:
> You aren't going to get better deals on tapeouts/IP than NVIDIA/AMD. You need some advantage.
> If you want a dataflow graph compiler, build a dataflow graph compiler.
Now explain why. Clearly Tenstorrent is happy to build Yet Another Abstraction Layer, so instead of bullying them over it you should at least attempt to actively humiliate them for the approach. You know, produce some manner of evidence that vindicates your position instead of relying on your authority alone. Jim Keller has no reason to take this seriously, even if you're right.
Without any numbers this feels like one cult of personality trying to bait another into a shit-flinging contest as a marketing scheme. We've seen this happen several times before on Hacker News, and it doesn't end up with either side making an Nvidia-killer. This is not a model for productive discourse.
Re: Advice to Tenstorrent
#3I thought George was going to save AMD. Now he's saving tenstorrent? Busy guy!
Re: Advice to Tenstorrent
#4I thought George was going to save AMD. Now he's saving tenstorrent? Busy guy!
Don't forget he was also going to save Twitter but noped out after a few weeks.
Re: Advice to Tenstorrent
#5With all due respect Mr. Geohot, you've got an awful lotta nerve to throw stones from your glass house. This guy needs to drop the middle school tough-guy tone and post numbers. The central thesis of this article is sound, lead with it: > You aren't going to get better deals on tapeouts/IP than NVIDIA/AMD. You need some advantage. > If you want a dataflow graph compiler, build a dataflow graph compiler. Now explain w…
I think you're right, mostly, but... While I'm sure Jim Keller will make great silicon, I'm not sure how good he's going to be at shaping the SW platform thing. I hope he will, I'm rooting for him, but I feel that this might be a novel challenge for him.
Geohot is abrasive to say the least, and, no, this is not a model for productive discourse(I'll try not to bring in some of his hot takes on the stream because giving them stage is probably also not productive) But I do think he has good taste in SW and he might be right about the number of layers of abstraction.
For context, geohot wrote this live on a twitch stream.
Re: Advice to Tenstorrent
#6I thought George was going to save AMD. Now he's saving tenstorrent? Busy guy!
Don't forget he was also going to save Twitter but noped out after a few weeks.
Maintaining and improving existing software sure is boring and often thankless compared to starting flashy new projects where you get to make and understand all the major decisions up front.
Re: Advice to Tenstorrent
#7Has geohot done anything since the original iphone jailbreak?
The ventures he has started (I can think of tinygrad and comma ai) all seem like half finished tech demos.
Re: Advice to Tenstorrent
#8Has geohot done anything since the original iphone jailbreak? The ventures he has started (I can think of tinygrad and comma ai) all seem like half finished tech demos.
He's the founder of comma.ai
Edit: you edited your comment after I told you he made comma.ai.
Bit dishonest, but whatever, I wouldn't describe comma.ai as a "half finished tech demo" but you're allowed to your own opinion about it.
Re: Advice to Tenstorrent
#9I thought George was going to save AMD. Now he's saving tenstorrent? Busy guy!
geohot has a loud mouth ... but he has earned the cred and walks the walk.
I wish there was a thousand more geohots than all the mediocre middle-managers at AMD or tenstorrent; or people who have never done anything beyond posting snarky comments in online forums.
Re: Advice to Tenstorrent
#10I thought George was going to save AMD. Now he's saving tenstorrent? Busy guy!
I think he is right about AMD but completely misses the mark when it comes to tenstorrent. He is ranting about exponential linear unit (elu), which hardly seems to be something that could possibly hold an AI company back. If the hardware is running and training models reliably, then it's just a matter of pricing to stay competitive. Poor optimization cuts your margins, but the incentives are aligned.
With AMD the experience is so poor that you have to save the company from itself if you want to make progress.