hankbond
thinking about how to accurately describe the problem at hand and figuring out the simplest way to approach it takes a lot of effort well before you get to the implementation step of coding.
What I like about this is that it feels like the new three rules are about focusing on the most successful human alignment technique of making the right thing the easiest. People will usually just do the easiest version of a thing they don't want to do so they can get back to doing what they want to do.
I don't know if that drive is universal or not tho. I have met people that experience pleasure from pain, but then again, is that actually pain?
It's possible that the audience for anyone that would plug in their phone to a KVM setup is just too niche to care. Just seems like with computing being so expensive these days, I really want to get the most out of my devices.
Running android in a DeX mode is fine, but its still android. Now that MacOS is already optimized to run on mobile chips, it seems so limiting that it can't run on iPhones just because of customer segmentation.
In most formal publications of The Before Times like newspapers and magazines, you did not want much of a writer's specific tone to come thru bc the organization had its own writing style. We used to value "correctness" because too much variance (without intent) made things hard to read—it was like context switching and came with a cost.
Nowadays though, so many people are already reading Claude writing day in and day out. I would venture to say that the opposite cost is being incurred now, where as soon as I start to see the same language patterns, some attention mechanism in my brain just starts to drift off. I literally cannot mentally focus on reading when the prose is 1:1 the same distribution as Claude. Some kind of fatigue happened by reading its output over and over day after day at work.
Anyway, just think about changing it up if you're interested in writing (even if it means your output is "sloppier").
I would try focusing on building a more unique style of writing, this feels like it went through heavy alignment to Claudes distribution. For the general audience maybe they aren't that sensitive to it yet, but for those that have to use LLMs at work, having to read more of it is grating.
Dang, that's rough.
> I realize that part of the reason I have not been able to appreciate a work of art before is because my mind tends to anxiously attempt to absorb information, without slowing down to absorb visual work in a linear fashion, rather choosing to keep track of as many details as possible from the image it perceives, then move on.
I would actually recommend not trying to ingest linearly (as in a raster scan) but as a Breadth First Search. Try to unfocus a bit (your eyes or your mind) and not analyze anything at first. The key is to maximize perception. Only after you are able to "feel" the piece should you dive into the details.
> profundity
word of the day?
Are they trying to say some negative outcome in Africa is caused by the Mercator projection?
Idk if "owed" is the right word here, and I disagree that the disparity is from being "smarter". There are plenty of people with high analytical intelligence that are not paid very much. Think about how poorly some very smart academics are often compensated.
Maybe I'm being reductive but it seems more simply that the disparity is based on "how much leverage/influence do you have over those with the money".
This is the one that really got me to giggle. I can tell this is going to stay buried in my brain for a while.
I always find maximalism jarring and this was certainly no exception.
very good way to put it.
I am currently building a piece of very modular software and it has been the hardest-to-design project of my entire career. I would never be allotted this amount of time-effort at any job I have held to make something this robust and clearly defined. Many aspects of this project have taken 3-5 rounds trying-and-trashing to get an abstraction that is uncomplicated.
This is precisely why vibe coding is so successful for building tiny isolated scripts, and so disastrous for anything else. It's just really dang hard to build something large and simple.
https://hank.bond/posts/highlighting-my-code-based-on-how-mu...
It makes sense to me that agents with known tool sets should be able to safely create ad-hoc "tool recipes" that are not arbitrary code execution but are kind of arbitrarily composable from allowlisted functions. After reading thru this thats what this appears to be.
I guess the addition of the json call graph makes this easier to wrap in a durable execution primitive for easy restarts.
> This presents a problem for the typical way that academic papers are written, which is to do all the work in a coffee-fueled fugue in the last few days before the deadline, then stay up all night writing the paper and finding citations for the pro-forma “related work” section which you did last but you know that the reviewers will insist upon
I have zero exposure to academia but chuckled because thats often what I do for blog posts :P
I have never had a "really deep conversation" about my career at a mid/full year review. Often, that's where I get feedback about something that happened months ago I was unaware my manager thought needed improvement.
The in-the-trenches feedback mentioned in the article would be an improvement over the lack-of-any feedback.
All of my favorite roles were actually not ones with the most interesting technical challenges, they were the ones where I felt like I had real leverage I could wield through my manager. If you want to get anything meaningful done, you need buy-in from leadership, and it's very difficult to get that when your manager is not on-board.