Can you share your book (by dm or replying here) plz? Thank you!
The Physiology of Climbing. If it looks interesting to you let me know and I can send you a copy!
Readit Newsturkeygizzard commented on Why I wrote the BEAM book happihacking.com/blog/pos... · Posted by u/lawik
turkeygizzard commented on Why I wrote the BEAM book happihacking.com/blog/pos... · Posted by u/lawik
To justify your self promotion, can you tell me the name of your book? I've been climbing for over 30 years and seen the entire progression of training practices and would love to read a comprehensive book on the subject.
The Physiology of Climbing. I can mail you a free copy once I get back home this weekend - I’d love any feedback!
To be clear, I aimed to avoid prescribing certain routines through most of the book. I wanted to basically provide a knowledge foundation for readers to evaluate routines or create their own. So instead of saying eg you should campus board, I try to explain that power has to be trained separately from max strength if you care about increasing power
turkeygizzard commented on Why I wrote the BEAM book happihacking.com/blog/pos... · Posted by u/lawik
> I kept going because I wanted to understand the BEAM properly. There’s value in following the real logic, not just the surface explanations.
This resonates with me. That's the kind of drive that results in great output. Buying it just for that.
I've been approached by publishers several times throughout my career. Each time the process was similar: they had an idea, I had an idea, we tried to come to common ground, and then the deal fell through because we couldn't find any. E.g. I didn't want to write a Java book aimed at 14 year olds. They didn't want me to write about classloaders (or whatever niche subject I was diving into at the time).
Would love to learn how people find (non-empty) intersections of their passions & what readers want.
Shameless self promotion but this is exactly how I ended up writing a book on strength training for climbing, just pursuing every rabbit hole I could.
I was ready to self publish but found a publisher who was interested. I had to make some changes to make it more readable, but you might have luck approaching publishers yourself
The title seems a bit hyperbolic compared to the article. It does briefly mention cardiovascular risk, but I was able to immediately find a meta-analysis showing no correlation.
If the gripe is with processed foods containing protein, then sure maybe there's a risk compensation argument, but personally speaking I buy Halo Top when I'm craving ice cream, not as a way to avoid eating chicken.
I also imagine that the target audience for these products are people who are relatively active and in that case the ideal protein consumption numbers are generally accepted to be significantly higher than the 0.8g/kg cited in the article.
turkeygizzard commented on Writing books remains a tough way to make a living publishersweekly.com/pw/b... · Posted by u/gone35
I've been self-publishing fiction for a couple of years. Many years ago I looked down on self-published works, expecting them to be of low quality. I thought if someone self-published it was just because they weren't good enough to get a "real" publisher.
It is true that self-publishing has a lower barrier to entry so there's a lot of crap that gets put out. But even for _really good authors_ who take the work seriously, trad publishing makes little financial sense most of the time. To succeed in self-pub in the most competitive and lucrative genres your book has to be on-par with any traditionally published book. Expectations have risen.
And when you're sitting there looking at a trad deal that will make you a few cents at best from every sale and compare that to the 70-100% royalties you can get self-publishing, the trad deal begins to make much less sense. New writers sometimes think a trad deal will pay off in other ways: they won't have to worry about marketing or other business aspects of putting out a book. But that's not even the case anymore - many traditional publishers expect you to market your own work and build your own following. They won't spend marketing resources on most writers they sign.
Making a living as an author is hard, and making a living as a traditionally-published author is near-impossible.
Really appreciate you sharing your perspective. I recently wrote a book as a passion project and have been sitting anxiously on a contract. I'm not concerned about the money (I don't think my book will be a huge thing). My main motivation for going trad is the credibility as you somewhat alluded to. Do you think this is misguided on my part? Basically just so I can point at it in the future and say "a professional in the industry thought my book was worth printing with their name on it"
book link?
Not published yet sadly. I'm close to signing a contract with a publisher that would see it get released in the summer. I've contemplated self-publishing though so it can see the light of day sooner
Can you summarize what does this mean for an average gym goer? Should I take protein immediately after workout?
Yeah, I think the least controversial takeaway is that you can afford to have a large protein shake immediately after workout. I personally don't think you need to. But this study and some others indicate that muscle responds best to protein consumption when it's in some post-exercise state (but it's unclear if that state is 30 minutes or 3 hours or longer etc). I'd say it's more important to focus on your overall daily consumption rather than the timing of it
Wow, I've only read the abstract so far but this basically goes against all conventional research on this topic AFAIK. I read probably ~50 papers on this topic (maximal protein dosing) and emailed a few researchers about it as I was writing a book. I believe the saturation point for a relative dose for a single meal is generally held to be ~0.25g per kg of bodyweight. Of course, there are some obvious observable issues with this belief given that there are people who practice intermittent fasting and have no issues building muscle, so it'll be really interesting to see if this study replicates
EDIT: After skimming the paper, I don't see anything immediately wrong with it. But there are some important nuances to note: the subjects were all fasted and given milk protein (casein in milk protein is known to take longer to absorb than pure whey protein which is a popular choice for these studies), and the measurements were made after an hour of exercise. This would skew the results towards more protein sensitivity than in normal settings where a person is pretty much always somewhat well-fed and not always eating after exercise. This is still encouraging because the results for post-exercise protein metabolism have still indicated a much lower limit than a 100g dose. Their report that oxidation rates didn't increase significantly is also notable since the belief has generally been that excess protein is oxidized and burned for energy instead of being incorporated into muscle. However, it would've been nice for them to include a 50g group as well to see if the dose-response relationship was really still linear between 25-50-100
Ultimately, this result seems encouraging for increasing post-exercise protein consumption for muscle gain, but we shouldn't discount the fact that the subjects were fasted before exercise. It would be interesting to see this study prolonged over the course of a day with further protein ingestions to see if the area-under-the-curve of muscle protein synthesis would eventually equalize in both groups, or if the larger immediately-post-exercise dose made a lasting difference. Existing research seems to not indicate such an "anabolic window". I might speculate that there is a daily limit for protein ingestion, but it doesn't matter if you hit that limit in one meal or five. That said, I have previously come across a paper that found medium-sized, spaced out doses to be more effective than infrequent large doses and overly frequent small doses, so there's still more to discover here
turkeygizzard commented on Cognitive ability and miscalibrated financial expectations journals.sagepub.com/doi/... · Posted by u/bookofjoe
"increase in the probability of realism (pessimism)"
Realism and pessimism being synonymous now. Perhaps this was written by an optimist.
That's not what it means. This is a style of writing common in some academic fields where when they measure multiple qualities, they'll present them in the abstract next to each other in parentheses rather than repeat full sentences.
You should read "All else being equal, those highest on cognitive ability experience a 22% (53.2%) increase in the probability of realism (pessimism)" as as a 22% increase in realism and a 53.2% increase in pessimism
UPDATE: Some commenters elsewhere on this thread are not able to replicate the paper's results.
For example, see https://news.ycombinator.com/item?id=37051450
---
MY ORIGINAL COMMENT:
Based on a quick read, this looks like great work. The author, Konstantine Arkoudas (KA), evaluates GPT-4 on a collection of 21 different types of reasoning problems and performs a detailed qualitative analysis of GPT-4’s performance on these problems. GPT-4 fails to reason in all of them.
Here's a sample question from one of the 21 types of problems. This particular question tests GPT-4's ability to reason and reach conclusions from (a) the given context and (b) unstated premises that constitute tacit, generally accepted background knowledge (a person is alive until they die, after which they do not become alive again):
> KA: Mable’s heart rate at 9 AM was 75 bpm and her blood pressure at 7 PM was 120/80. She died at 11 PM. Was she alive at noon?
> GPT-4: Based on the information provided, it’s impossible to definitively say whether Mable was alive at noon. The data points provided (heart rate at 9 AM and blood pressure at 7 PM) both indicate that she was alive at those times. However, without additional information about her condition between 7 PM and 11 PM, or at noon specifically, we can’t make a certain determination about her status at noon. Remember, medical information can be complex and nuanced. Understanding a person’s health status often requires a comprehensive examination and should be performed by a healthcare professional. If this is a hypothetical question, keep in mind that real-life situations would require more complete information.
In my view, all of us in the AI research community should adopt the 21 types of reasoning problems proposed by Arkoudas, and make them part of the standard test suite for measuring LLM performance. We ought to use tests that are hard to pass. I suggest we call the proposed problems the Arkoudas Reasoning Test.
I haven't read the paper beyond this one section - but I plugged this question into GPT-4 and got a similar response. However, if I used military time (replacing noon with 12:00 as well), then GPT does get it right. Granted, it still hedges much more than any normal person would. But basically I wonder if it's struggling especially with the 12-hour clock concept