I have both an Apple Watch 8 and the Garmin Fenix and I use the Fenix for sleep tracking. I find the Apple Watch to be too general with the stats. The Fenix gives a lot more detail. You can debate if the extra detail is useful or not. I also like the heart rate variability tracking with the Fenix (it seems to mirror how tire I feel pretty well). Lastly, the Fenix can hold a charge for several days. I can use it to sleep track and run and repeat and it charges quickly. If I sleep track with my Apple Watch, it may not have enough battery for the rest of the day. I run with both -- the Fenix for running specific tracking and the Apple for calling friends, listening to Audible, or podcasts.
That would be an understatement, are you running/cycling a lot outside, or is it a smaller model (thus small battery because physics)?
Mine (Fenix 7) holds charge for 15 days minimum and that's with tracking workouts 3-5x/week (no GPS though, winter so I treadmill for runs). On a couple of months where I didn't do sports it held up 25-30 days.
I have SpO2 tracking disabled because it's quite battery intensive and the only use for it would be high altitude acclimation, although I must admit I looked at it during my "stop smoking" process.
my experience with garmin (vivoactive, not fenix) was that they had all kinds of precision and detail, but it also didn't even notice when i got up to pee in the middle of the night - just a straight line through the graphs as though i hadn't woken up at all. that was the end of my trust in their sleep tracking.
Mine reliably notices that I woke up and immediately go under when my wife comes home late in the night, which happens basically every day (because bartender) so I get somewhat statistically significant results in that regard.
The Quantified Scientist does very detailed, measurement-based tests on all sort of smart watches, you might want to see where your device stands in his charts in terms of accuracy.
my garmin was really good at picking up my heart rate. there was one time i had it in a waist pack, and i was wearing a chest strap that was not paired to the garmin, and the garmin managed to pick up a pretty accurate heart rate for most of a bike ride.
I recently got a Fenix 7, but not for sleep tracking purposes. I find it ok. I definitely think it isn't great at measuring wakefulness at night, but I also have a very low HR and high HRV (while awake), which so this causes the margin for error in the device to be very low.
As I usually say, all of the devices are good enough. You're getting historical data about what your body did. You can't go back and change it anyway. I don't see real value in knowing my historical sleep data.
Not OP but I have a Fenix 7x. What happens very infrequently is that I would wake up during the night, and then be absolutely still (I'm trying to go back to sleep) except for checking my watch every 15-20mn. This does not get detected as "awake" the following morning.
I don't really care because I got this watch so I can upload a track and follow it while recording various metrics during 5+ days, and for this it works perfectly.
There are two data points you need to accurately track sleep: Motion and respiration rate. With that information you can identify light sleep vs. deep sleep, and sometimes you can differentiate between light sleep and being still.
Source: Worked on the ResMed S+ and got a theory dump from the PhDs running the project.
Sleep versus awake from a sensor on the wrist is always going to be subject to wide error bars.
Source: worked on an experiment trying to make people fall asleep while driving (in a simulated environment so it was safe- I built the simulated environment). It took a lot of EEG wires and gel in subject's hair etc. to accurately figure that out.
Same experience for me. If I wake up but lie still it's not nearly as accurate. What I do find useful is the Body Battery score, that generally maps well to how I feel the next day. And the Stress Score is an eerily good indicator of when I'm getting sick and when the illness is stopping.
Data aside, neither are ideal. I can’t sleep with the Apple Watch because it needs to be charged while I sleep to get through the day, and the Fenix is too heavy for my wrist at night. I use an old Mi Band, which tracks approximate data that suits me.
According to reviewers, Mi Bands and generally all of Xiaomi's devices are fairly bad at sleep tracking. So much so that it's almost pointless to use them for that.
I know it’s fully anecdotal, but my Xiaomi/Huami (former Xiaomi sub-brand) devices have matched up sleep duration quite well with what I feel in the morning - and I’m quite sensitive to less sleep. I think it’s quite good for sleep duration, but I don’t rely on REM duration etc as I don’t have much use for it. When it predicts a good sleep score I’ve definitely slept well, though sometimes it gives a lesser score even when I don’t appear to have slept poorly.
(I’ve used a Mi Band 1, an Amazfit Bip, and currently an Amazfit Band 7.)
FWIW, I charge my watch while taking a shower before bed and in the morning, and that seems to be enough to get me through the day and through the night.
I disagree on your 14th century building picture being "nothing special" to Europeans. All the major German cities that I've lived in were bombed to ashes in WW2. Most buildings are post war construction. Picturesque towns like Tübingen with conserved old buildings are an exception in Germany and attract local tourism for this reason. Split is a UNESCO world heritage site and pulls in tourists from all over the world.
Cities were bombed to smithereens but a lot of smaller towns in the countryside were spared. My Dad grew up in Berlin during WWII but my mom just a bit north in Mecklenburg, big difference between their wartime experience.
While that is true, all towns and villages under 80,000 inhabitants in my area (100 km around the village where I grew up) had historic centers with (at least) dozens of buildings that looked like my example from above, and were spared in WWII. These old half-timbered houses are so extremely common here that as a child I thought that all towns and villages looked like this.
Huge archive that's heavily biased towards text adventures / interactive fiction. There are only three titles published by Lucasfilm Games, and they predate Monkey Island.
> "Basically nobody writes CUDA," wrote Keller in a follow-up post. "If you do write CUDA, it is probably not fast. […] There is a good reason there is Triton, Tensor RT, Neon, and Mojo."
> Even Nvidia itself has tools that do not exclusively rely on CUDA. For example, Triton Inference Server is an open-source tool by Nvidia that simplifies deploying AI models at scale, supporting frameworks like TensorFlow, PyTorch, and ONNX. Triton also provides features like model versioning, multi-model serving, and concurrent model execution to optimize the utilization of GPU and CPU resources.
> Nvidia's TensorRT is a high-performance deep learning inference optimizer and runtime library that accelerates deep learning inference on Nvidia GPUs. [...]
Keller was speaking of OpenAI's Triton (https://openai.com/research/triton), a Python-like language that is compiled to code for Nvidia GPUs, but Tom's Hardware mixed this up with Nvidia's Triton Inference Server, a higher level tool that's really not a replacement for CUDA and not directly related to the Triton language. Easy to confuse these if you are a writer in a hurry.
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.
Yeah, this review is pretty superficial. It seems like it was written by a college freshman that barely engaged with the interview. (Thanks for sharing it though.)
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.
Isn't low-level hardware really at the heart of a lot of this? Hasn't a lot of the criticism of Cuda been that it's incredibly difficult for others to implement on other hardware bc of the low-level interactions and Nvidia's usage of dark-APIs (can't recall the term i've heard used).
Wasn't this one of the reasons AMD abandoned/deprioritized their efforts on such a project?
The Marvelous Mrs. Maisel was fabulous. They had lot of good shows in the prestige comedy or dramedy (is that still a thing?) genre. Transparent, Red Oaks, Mozart in the Jungle, Fleabag (bought from BBC)
Less weight on the parts of the body that move most during a run is an obvious benefit of not wearing shoes.