Other prompts. Usually working 3 tickets at a time in parallel. My company's contracts make #tokenmaxximg a thing still. When this ends, I'll probably be researching another ticket to reduce context and token cost on my next prompt. More like making sausage than code, but that's the world we've always been living in as far as the C-suite is concerned.
I think the problem here is that we have a bias for those who agree with us that outweighs our patience in searching for oppositional opinions that are well founded. From a liberal bubble it is quite hard to find conservative viewpoints that aren't based on unobserved apriori belief or strawman arguments. It feels like being a heavyweight surrounded by lightweights and it makes me feel like I need a better sparring partner, I just can't find one...
> I think the problem here is that we have a bias for those who agree with us that outweighs our patience in searching for oppositional opinions that are well founded.
This is a very agreeable statement, but I'd add that politics is not about finding the Kantian truth of what's best for everyone (inside the country? globally? also immigrants? lazy and ugly natives?).
It's about balancing interests. Of course, the idea of free market democracy was/is that both goals eventually converge.
I'm thinking you're meaning like "politics is about trying to understand/impact what could plausibly occur", whereas the "truth" you mention is inherantly unconcerned with that, but I think there's also value in finding and debating it.
What's implementation without a target? Is politics concerned with improving conditions for people, or is it just balancing enough interests that we don't start killing eachother?
It's shades of both I think, and there's fierce disagreement about both the global optimum and how to or if it's worth getting there
I thought about balancing the interests of those who have power, by all means short of war.
And of course this begs the question who has power and who should have power.
The will to improve living conditions comes from the interests of those who have political power, in my view. You can say because of democracy if you like. Or, more cynically, dependence on labor and consumption (Fordism), or, more idealistically, ethical values in powerful people themselves, and all of that are nuances and not absolutes I guess.
But I wouldn't say that my definition was precise.
I just wanted to point out that it is not a given for politics to have the goal of optimizing utilitarian interests, maximizing wellbeing or long-term goals such as protecting people.
In other words, participants in politics do not only discuss how things should be achieved, but also what should be achieved.
If that makes sense: this is what I meant by "balancing powers". I'm not sure right now how to map it to the two poles you describe.
IDK about the 2400 year old argument (apparently against paper), but if you need to use AI to organize your book find something else to do. If you don't have the patience or motivation to learn and do this, why should a reader have the patience to read the book. Most people who use AI in their creative process don't understand the creative process. Having something trained to do what came before to help you do something new is like putting guardrails on yourself to prevent you from doing something new. It feels right when you're doing it, but that's why they can charge for it. Like Coka-Cola -- It tastes great while you're drinking it so you buy it. After a while of this it puts your pancreas under distress leads to a myriad of health problems (diabetes, heart disease, kidney failure, cancer) that could have been prevented by just not drinking Coke.
Even as a developer who uses RPI skills with models, I watch them write utilities that already exist, make inline functions when a utility class that it would logically fit in goes untouched. Bloat isn't just because of vibe coders, it's the nature of the technology. Writing code by hand is like drawing with a pen. The developer plans ahead, gets the shape of the code in his mind and writes just what is needed. A process of genesis. When using an LLM this same coder architects the shape of the code and asks the LLM to carve it from all the examples in its training data. A reductive process. The problem is that sometimes the shape doesn't confirm to the training data or the model doesn't share the developers architectural aesthetic. At this point imposter syndrome can set in and the developer accepts what the LLM wrote without the careful planning and thhought that went into the original approach. This leads to missed edges and curlicues in the code where an approach may not be fully understood (bloat). Since we're approaching the limit of quality that LLMs will reach, this will be what keeps software developers employed. Either building new systems or logically correcting brownfield codebases that have bloated over time. Having the patience to read through the bloated code and direct refactoring as well as being able to spot bloat/tech debt early will be the fundamental employable skills.
Meanwhile in the US the laws are being changed to protect the wealthy, while the current administration is siphoning value of national assets into their own pockets. The poorer the country, the more likely this is to happen. I wonder how long it will take for warlords to set up shop in Kansas...
Or is it all a nice story that matches the scifi we have been consuming for the past 50+ years. If these LLMs are all trained on the same data, what do they gain from "sharing information" on a chat board. This sounds like what humans with different backgrounds would do when they cosplay as computer hackers.
Each of those agents ends up making "decisions" that lead it to look at some things over others. Given infinite the same agent could eventually fully explore all those options, but each one explores things a bit differently due to different forks in the road due to randomness in token generation. Thus sharing information is useful.
Will the original artists come for royalties or will OpenAI? Or both? Facebooks motto was "move fast and break things" the AI industry motto should be "break things and make fixing them everyone else's problem".
reply