Wow, that's some omission in the article. Mentioned in the very bottom, but with no disclaimer that it might influence his opinion as they're a competitor:
> His statements also imply that even though he has worked stints at some of the largest chipmakers in the world, including the likes of Apple, Intel, AMD, Broadcom (and now Tenstorrent), we might not see his name on the Nvidia roster any time soon.
I'd tend to lean this way. Keller is someone who could generally call any chip company in the world, and have a top job tomorrow. Not some scrappy dreamer who's just trying to steal customers from a big player.
The field itself is already pretty niche. The amount of people on his level probably fit on an index card. That helps probably the most.
He's obviously a smart guy, but to me his wisdom comes from being able to actually understand the system and explain it. Whether he actually codes it or is even that smart becomes irrelevant, he has the ability to big picture it and get aces in their places.
But mostly the first point. The niche is so small you'd probably be hard pressed to find someone in comments who actually has worked alongside him to even attest to any of this.
It's immensely clear that when he goes somewhere, some big advancement usually happens, and he can explain why. Even if that's -all- he knew, it'd be enough to make him super valuable. So if we have to keep going back and pinning traits, I'd say it's some amount of intelligence mixed with a whole lot of passion.
I meant more in terms of the article content. The entire article is about his point-of-view, but it's surely useful to the readers to know if he's just someone who happens to have an opinion, or if he also directly competes with the project/company he is talking about. But they never say that.
Somehow, I don't see him going to Nvidia in any case. Their designs are very different from his philosophy, and he can be quite opinionated. I'd characterise Tenstorrent as his attempt to build the opposite of an Nvidia style accelerator.
If only there was a service that could watch a 2 hour video and give you a detailed answer to this question in a few seconds just by asking it… soon enough I guess.
Feeding the output of a transcription service (e.g. https://youtubetranscript.com/?v=G4hL5Om4IJ4 ) into an llm for specific requests should be possible, likely in multiple steps to handle context limitations
Gemini does that already. Here's the output when asked what is Keller's philosophy given that youtube interview:
According to the video, Keller’s philosophy emphasizes the importance of both theory and engineering in the field of computer science. He believes that theory provides a foundation for understanding how things work, while engineering is the practical application of that knowledge. He argues that both are essential for making progress in the field.
Keller also emphasizes the importance of craftsmanship and attention to detail. He believes that the best engineers are those who take pride in their work and are constantly striving to improve it. He believes that this is essential for building high-quality, reliable computer systems.
Finally, Keller believes that it is important to be open to new ideas and to be willing to experiment. He believes that this is the best way to make progress in the field of computer science.
Here are some specific examples from the podcast that support Keller's philosophy:
- Keller discusses the importance of theory in the development of branch prediction, a key technique for improving computer performance. He explains that while the basic idea behind branch prediction was known for many years, it was only through theoretical advances that it was possible to develop a practical implementation.
- Keller also discusses the importance of engineering in the development of the Alpha 21264 microprocessor. He explains that while the chip was a groundbreaking design, it also had some flaws that were only discovered after it was released. He says that these flaws could have been avoided if the engineers had paid more attention to detail.
- Finally, Keller discusses the importance of being open to new ideas. He talks about his work on the TenstorFlow chip, which is a new type of chip designed for machine learning applications. He says that he was initially skeptical of the idea, but that he eventually came to believe that it had the potential to be a major breakthrough.
Overall, Keller's philosophy is one of pragmatism and open-mindedness. He believes that the best way to make progress in computer science is to be willing to experiment and to learn from both successes and failures.
...
Here are some timestamps related to Keller's philosophy in the YouTube video:
1:18:02 - Keller discusses the importance of both theory and engineering in good design.
1:23:22 - Keller gives the example of branch prediction as a breakthrough in engineering that was based on theory.
1:34:12 - Keller talks about the importance of craftsmanship in engineering.
1:42:15 - Keller discusses the limitations of human thinking and the importance of being open to new ideas.
2:12:22 - Keller talks about the responsibility of engineers to society.
No, he showed up way after founding, he might have been an advisor before though. I'm not sure what the founding CEO is up to now but he had worked in AMD's GPU group and might have met Keller during that work.
> His statements also imply that even though he has worked stints at some of the largest chipmakers in the world, including the likes of Apple, Intel, AMD, Broadcom (and now Tenstorrent), we might not see his name on the Nvidia roster any time soon.