The glorified autocomplete. Why would the LLM "work on something else then get back on this", is it's subconscious going to solve the problem during that time?
But because people say it, it says it too. Making sense is optional.
Ive found that clearing the context and getting back to it later actually DOES work. When you restart, your personal context is cleared and you might be better at describing the problem you are solving in a more informationally dense way.
Now if only you had read to the end of my comment, to recognize that I was setting up for something, and also applied not just one but several HN guidelines (https://news.ycombinator.com/newsguidelines.html, under "comments")...
> I don't particularily care if people can write code like they work at the assembly line. I care [...] That they can deliver business value quickly.
In my experience, people who talk about business value expect people to code like they work at the assembly line. Churn out features, no disturbances, no worrying about code quality, abstractions, bla bla.
To me, your comment reads contradictory. You want initiative, and you also don't want initiative. I presume you want it when it's good and don't want it when it's bad, and if possible the people should be clairvoyant and see the future so they can tell which is which.
I think we very often confuse engineers with scientists in this field. Think of the old joke: “anyone can build a bridge, it takes an Engineer to build one that barely stands”. Business value and the goal of engineering is to make a bridge that is fast to build, cheap to make, and stays standing exactly as long as it needs to. This is very different from the goals of science which are to test the absolute limits of known performance.
What I read from GP is that they’re looking for engineering innovation, not new science. I don’t see it as contradictory at all.
You should worry about code quality, but you should also worry about the return on investment.
That includes understanding risk management and knowing what the risks and costs are of failures vs. the costs of delivering higher quality.
Engineering is about making the right tradeoffs given the constraints set, not about building the best possible product separate from the constraints.
Sometimes those constraints requires extreme quality, because it includes things like "this should never, ever fail", but most of the time it does not.
> You want initiative, and you also don't want initiative. I presume you want it when it's good and don't want it when it's bad, and if possible the people should be clairvoyant and see the future so they can tell which is which.
The word you’re looking for is skill. He wants devs to be skilled. I wouldn’t thought that to be controversial but hn never ceases to amaze
Some of our code is of high quality. Other can be of any quality as it'll never need to be altered in it's lifecycle. If we have 20000 financial reports which needs to be uploaded once, and then it'll never happen again, it really doesn't matter how terrible the code is as long as it only uses vetted external dependencies. The only reason you'd even use developer time on that task is because it's less errorprone than having student interns do it manually... I mean, I wish I could tell you it was to save them from a terrible task, but it'll solely be because of money.
If it's firmware for a solar inverter in Poland, then quality matters.
> people who talk about business value expect people to code like they work at the assembly line. Churn out features, no disturbances, no worrying about code quality, abstractions, bla bla.
That's typical misconception that "I'm an artist, let me rewrite in Rust" people often have. Code quality has a direct money equivalent, you just need to be able to justify it for people that pay you salary.
I think Musk cares about revenue more than pissing off some random customer in Germany. As long as you don't stand out from the crowd, he'd rather have your $40. Use a VPN to be sure.
I mean no offense by this, but intuition literally means acquiring knowledge without an explanation. Did you mean experience or are you telling GP that you cannot explain how you do it?
No that is not what it means. I did not mean experience; I did not mean that I cannot explain how I do it; I meant what I said: intuition. I can explain how I do it; I can even explain how it works (as far as I think), but I don't really know how it works, and I don't care. I just care that I can do it, and that it works.
They mean to distinguish intuition, which draws on experience and can only be reflected on, from experience, which deals in actionable heuristics. Any appeal to intuition you make will fall on experiential advice when pressed. Intuition _works_ here, but if you mean to share your wisdom, you must translate it through experience, which is the actual concept we communicate through.
Essentially yes, thanks. I was focused on the difference between “I used my intuition (which you cannot be taught because I cannot explain it)” and “I can explain how you can develop a skill”.
Not possible, you're likely using the wrong words here. See https://en.wikipedia.org/wiki/Intuition which does mention the modern misuse to mean intuition and reasoning combined. Anything that uses conscious reasoning (and thus can be taught or acquired as a skill) is not intuition.
Conveniently sidestepping the discussion of "should we care". I don't know how many people care or not, but I think more would care if the situation and implications were better known. It's good that this is brought to attention, and to say "people don't know so let's not talk about it" is absurd.
There exists a concept called "regression to the mean". I don't think "regression from the mean" means anything.
There is no way pilots form all over the world could "regress to the mean". They could not have been all, or most, "above the mean". The mean would be higher then.
What rules can you possibly have that distinguish the expert and the manipulator in all cases, without abuse?
I think free speech comes from the same base as universal vote: any selection mechanism would be corrupted and in the end cause more harm than good. That is why the solution is to let everyone speak / vote. If you have some uncorruptible people or mechanism for selection, just use that to make policy decisions directly.
I think the solution is to elevate critical thinking in the populations, so people can be less vulnerable to psychological warfare. Otherwise you're just picking a different manipulator - whoever writes or enforces the speech limits.
I think the solution is to elect a commission of experts to be deciding this. Term limits. Separate independent institution from the government - no meddling.
Critical thinking even in those capable of it is a limited resource. I can't spend all day every day critically examining every single statement the internet flings at me - it's mentally exhausting and wears one down.
Elect by the people at large? People who voted for Trump and such? What's the point in an elected institution separated from the government - the government is already elected, and people will mostly vote for candidates from the same parties in all elections.
Besides, "elect a comission of experts" is a contradiction. Experts are not elected. Expertise is not determined by voting. You want to appoint or select a comission of experts, or elect a comission of politicians. These are the choices. Appointment or selection will be done by someone else, likely politicians too.
You just hope some incorruptible competent people will get there by magic. They will not.
If you could do this, just elect a comission of experts to run the country, instead of this "truth comission" that makes sure people are well informed to vote correctly in elections for the real government, which will in turn run the country. Why do the indirection? There is no reason, if you could "elect" good people, but you can't.
So who gets to decide? Someone who is above influence? Who is that?
There has to be a lot more nuance. I clearly see that both Putin and the CCP do a lot of things predicated on the exact claim that their respective populations can not be left to decide for themselves. "People left free would make bad decisions, we the rulers are morally obligated to force them into a good path". I think this is the ostensible meaning of "freedom is slavery".
There has to be nuance yes. But the nuanced position starts with accepting the reality that a ton of people are indeed having their brain turned to goo. Just go outside of the bubble of somewhat tech literate highly educated young people and look at what 60+ year olds consume on Facebook.
There's AI generated content with tens of millions of views that is as fake as ancient aliens on the history channel but nobody seems to realize it. If you comment here there is a high chance you did not grow up among people with 8 years of basic education who haven't read a book in 20 years and believe quite literally everything they see. That is what a decent chunk of any population is like. The biggest blind spot of well-educated internet libertarians who taught themselves how to code at 15 is that they in all likelihood have no concept of how the average citizen navigates the world.
The problem with Putin isn't that he thinks a country needs intelligent and wise leaders, Plato would have told you the same thing. It's where he's steering it that's the issue and that the country's leadership is no more capable at the top than it is at the bottom.
But because people say it, it says it too. Making sense is optional.
reply