Cosine Thoughts

Today was a good day at practice. A very good day. I had mentioned previously that one piece of advice I had received was that I was making too many corrections. I got to start addressing that in practice this evening and something weird happened. Actually, two things. First, I don't feel like I've fired more than 1 or 2 arrows despite firing more arrows tonight than I do in a normal practice. And second, I was actually able to find time to think about and apply feedback. That first point is unexpected. I just kept practicing and firing more arrows and never seemed to get tired. The best I can guess is that the act of making all of those little adjustments was causing me to tense up far more than normal and that the corrections themselves may have been doing even more damage to my form than I had thought possible and thus increasing the wear and tear on my body.  Honestly though, I think it is the lack of tension. I wasn't able to completely stop myself from making adjustm...

I find writing down my thoughts helps to internalize things and get the most out of things like advice or observations. So, here is the first post in my run-up to testing for Ni-Dan later this year. Internally we had an internal "mock" shinsa at out dojo to see who the instructors felt were ready to challenge for their respective Dan in either the upcoming video or in-person Shinsas. My result? After a pretty good result in an earlier internal shinsa, I regressed a bit. I still got the green light to go forward with a few areas of note that I need to work on. Some from their perspective, some from my own, and some from a pair of guest instructors from the day of the mock shinsa that likely saved me from failing out completely. I'll start with my own thoughts. I always need to work on rhythm and timing with a TACHI . I'm doing video shinsa, so that is less important to testing this time, but would be critical for any in-person shinsa. And beyond Ni-Dan all testing is i...

Why do companies keep trying to use AI/token usage as a performance metric? Because they've lost (or never had) the ability to quantify success. Put another way, it is the exact same reason that vibe coders exist and succeed until they fail. AI is not currently reliable and the people who tend to rely on it most, also let it replace their own judgement and faculties. And they let it get that way because of a few (sometimes big) early wins.  Tokenmaxxing is an obvious result of an obviously flawed system.  How is the system "obviously flawed?" I've written up a number of examples of my struggles with AI at work. But it boils down to this; AI isn't actually "smart" in the human sense and the results are non-deterministic. This means that the 2 developers using identical prompts can wind up with WILDLY different tokens spent for the same problem. AND more than likely, the developer that spent more tokens ends up with the inferior solution.  Identical prompt...

I've already made my arguments against AI on a financial level and on a technical level. Now they've started suggesting that you combine these catastrophes into one big, uber-catastrophe: don't even write prompts any more, just write loops! The hubris! AI is not ready. Period. I'm NOT saying that AI will NEVER be ready. I'm saying that, at the current moment, we're not there. Not even close. If you thought the crazy AWS bills of the past were something, wait until the first engineering teams start taking this advice. I guarantee you that it will be epic. A little part of me actually wants companies to just take this advice and let Claude run without any token caps. Why? Not because I want to see those companies fail, but because I want to see how fast Anthropic can destroy itself when these companies suddenly can't afford the bills which they need them to pay to keep the lights on. It would be short term pain for long term gain in the software industry. A me...

A recent development in the past year or so at our dojo has been an "internal shinsa" to test for whether or not the dojo leadership would allow us to challenge for the next shinsa. I love the idea. My own feedback? I wish I had done worse. I have a problem. I don't like positive feedback. It doesn't tell me much. By no means was the performance perfect, and there were critiques. They were simply stifled by the positives. It deflates the sense of urgency and need for me. I suppose that there is an up side. It forces me to be the negative one. We didn't get to see the recordings, so I can only focus on what I was told and what I normally don't do well. And that too is a blessing in disguise. That performance was singular. Both in the literal sense and in the sense that I was feeling REALLY GOOD that day. I've never been able to perform so "freely". So, in some sense, focusing too much on that performance might not be as helpful. The critiques I di...

No. At least, not yet. Then again, we also should not have scrapped the carbon tax. There are a few key pillars to my reasoning: The government is operating a deficit. And a big one. This helps. The world is currently in an energy crisis, and anything which promotes reduced consumption is a good thing. Prices in Canada are currently much more favorable than most other places. There are other things that the government can do to help. Some of it with that money. The first point is pretty obvious. Higher gas prices means that the government makes more in tax revenue from oil and gas. At a time of economic uncertainty, when the government is already trying to spend its way out an economic crisis this is actually a bit of good luck. And we shouldn't turn around and piss that money away. The second point is also kind of obvious. The straight of Hormuz being closed means that there is less oil and gas to go around. We shouldn't be cutting prices to help us pretend that this isn't...