Hacker Newsnew | past | comments | ask | show | jobs | submit | parasti's commentslogin

> We do not optimize for time spent in ChatGPT.

So ChatGPT constantly ending all responses with tangents and followups is not for engagement?


Been using git since 2008, and this looks more intimidating than helpful. git rebase takes a list of patches and applies them one by one on top of a given "base" commit. And that's it. It's not all this complicated git command soup. It's just patches. No objects, no sha1s, no metadata, no branches, just literal textual diffs applied in order. It's the dumbest and also one of the most powerful things about git if you care at all about a readable history. If you don't, that's fine, but in some circles, e.g. most (if not all) open source projects, patch management and history hygiene is a very important part of good collaboration.

The tech that you are defending is going to put your profession out of work. If you can write a prompt that gets you exactly what you have imagined for your movie, then your entire craft has been obsoleted and can now be achieved by anyone with an imagination (or even without).

You're romanticizing, sadly. Every time I see someone scratching off numbers, I see a twisted industry exploiting human hopefulness and naivety. Dreaming costs nothing.


Scratch offs are a different beast than big games like the PowerBall


Gambling addiction is such a crippling disease. There should be accredited gambling laws so people can't gamble what they don't have.


When I see office workers walking off to the dreamer highrise offices in the sky, I enviously dream of being that worker in the sky, with all those dreams of grandeur.

Dreaming does cost nothing.


I really tried to get into the vibe coding thing - just describe the thing I need in human language and let the agent figure it out. It was incredible at first. Then I realized that I am spending a lot of time writing clarifications because the agent either forgot or misinterpreted something. Then I realized that I am waiting an awful long time for each agent step to complete just to write another correction or clarification. Then I realized that this constant start-stop process is literally melting my brain and making me unable to do any real work myself. It's basically having the same effect as scrolling any other algorithmic feed. Now I am back to programming myself and only bouncing the boring bits off of ChatGPT.


> Then I realized that this constant start-stop process is literally melting my brain and making me unable to do any real work myself. It's basically having the same effect as scrolling any other algorithmic feed

Yes, it’s extremely soul sucking. With the added disadvantage of not teaching me anything.


I felt this way too until I decided that my goal isn't to know things, it's to ship things.


I felt this way too until I decided that my goal isn't to ship things, it's to ship, support and improve existing things.


If your job is not to know things, just to prompt an agent to ship things, why would you have a job in a year?


Sounds very depressing.


One trick I have tried is asking the LLM to output a specification of the thing we are in the middle of building. A commenter above said humans struggle with writing good requirements - LLMs have trouble following good requirements - ALL of them - often forgetting important things while scrambling to address your latest concern.

Getting it to output a spec lets me correct the spec, reload the browser tab to speed things up, or move to a different AI.


One thing that helps is to write an AGENTS.md file that encodes the knowledge and tricks you have of the codebase, like running a single test (faster feedback cycles), common coding patterns, examples, etc.

I went full meta and sketched out a file, then had an expensive LLM go through the codebase and write such a file. I don't know if it's any good though, I only really use coding assistants to write unit tests.


I don't have much experience with it either, but what has worked so far is breaking down the problem into very small steps I can verify easily.


At this point it's easier to just write the code. If my prompt is to be longer than the code produced, why bother with explaining that to LLM?


The delta between "make a small requirement that you can check and verify" vs "create the code yourself" is pretty big. A well crafted sentence can sometimes still be hours of work.


Implicitly you appear to be saying that we need to reach that point before action is taken?


We need to have a reason to take aution before we take action, sure.

This is an incredibly niche product in Europe, so far I’ve seen no evidence that the current state of affairs isn’t perfectly fine.

No need to fix things that aren’t broken, or don’t even look to be trending in that direction.


The question seems legit to me.. Otherwise worded it's essentially whether there's correlation between both. Without evidence it's more difficult to justify regulation. At the end of the day a pickup is adjacent to a midsize van. To me, both seem like you're essentially getting hit by a wall...


The difference is visibility, with a van you can often see as close as 1,5 m in front of you due to the short hood. The problem is a lot of the newer trucks and SUVs are so tall that a full child (or 5) just disappear in front the car.


I upvoted but I was not taught this! I have had to slowly figure it out on my own. Writing things down is kind of like augmenting your brain. It's a memory that does not forget. When working through a problem, writing it down tends to point out the holes in your understanding. A corner case is never lost or forgotten when written down, it just stares at you until you write down a solution. The next step after realizing this is to develop the discipline to write things down and to organize your environment so it's effortless to write things down.


Same, I had to learn this the hard way. In fact, I find that many (younger me included) are arrogant about *not* wanting to deal with writing due to it feeling like waste of time. But after maintaining codebases for 5+ years, you begin to appreciate younger you explaining wtf you were thinking.

And now, being at a point in my career where I have opinions on many things and discuss them with peers, I slowly realized writing about it was actually helping me more than anything.


Using something like confluence religiously in a team is a big boon. Write docs about everything. Write to get decisions done, to plan, to celebrate, to retrospect, to architect, to help oncall. Everything! Doesnt need to be beautiful prose - just needs to be famn useful and ideally easy/quick to read.


"Eating sugar" and "reasonable amounts of sugar in your diet" are two very different things.


Sure, but like literally anything else, the dose makes the poison.


As a EU citizen, I don't care? People are not swayed by political ads. They're swayed by influencers who push political agendas covertly.


I would think this is naive to imagine that targeted ads do not have influence when used in large numbers. There is a reason why this market exists.

I am happy this law has an effect and potentially opens the doors to other players.


I think this comes from a us perspective in most of Europe political ads consist of a portrait image of the politician and a slogan that gets penetrated to death. We don't have attack ads here most of the time we don't even have ads that transport a message besides this is Dude A from Party A.


I can actually give a very specific real life example of political ads working because I have a friend who was part of the campaign. In Ohio there was a constitutional amendment on the ballot to legalize abortion. The orgs that spent millions of dollars getting it on the ballot were constantly polling to figure where they stand in terms of it passing. As a just in case they made a "break glass" ad campaign which talked about a 10 year old rape victim that had to be driven across state lines to get an abortion. At the 11th hour a few days before the vote they realized it wasn't going to pass. So they took that ad and blasted it across the state, you legitimately couldn't watch TV for more than 30 minutes and not see it at least twice. It covered every streaming service, youtube, facebook ads, tv. The polls went from 48-49% to almost 60% in favor and it passed.


Political ads definitely do sway people. Especially the shit-flinging ads are effective.

The ones where a political figure lays out the bare basics of their programmes don't make a lot of impact, but the shittier the party and the more manipulative their advertising, the more these ads have an effect.

The influencer problem is even bigger, of course.


Then why are they paying for them? They can literally see the exact CPC and CPA / CPM ratios that justify their spending


Ads influence people a lot. In particular the elderly generation.


My cousin says there should be a maximum voting age. She says if people can't vote for the first 18 years of their life, why should they be able to vote for the last 18 years (e.g. if retired or older than 65)?

I disagree, of course. I don't talk to this cousin anymore. Personally I think the very elderly contain the wisdom for future generations, and make the best decisions because of all that wisdom, so they should really be in charge of everything.


The elderly will die before they see the consequence of them voting in another conservative party that reduces climate goals and investments in public infrastructure. Young people have to deal with the fallout for much longer


What is your general opinion on the wisdom and decision-making of politicians and heads of state that are above the age of 80?


Anyone who is 81 or older is elderly, therefore they have a lot of wisdom, therefore their decisions are the best. My opinion completely aligns with this logic with no deviation.


Agreed. As a Frenchman, I can testify that the same logic allows anyone to take perfectly dreary 2022 Napa valley wine, and turn it to a beautiful 1942 Saint-Emilion. You just need to age it 80 years.


> elderly, therefore they have a lot of wisdom

That’s a hell of an assumption, though maybe this is missing a ‘/s’?


And the younger generation are influenced by influencers, which are also ads.


You are not immune to propaganda


I don't disagree but I feel like having spent a couple of decades filtering bad Linux advice on sketchy forums has honestly built up some resilience.


Europeans are famously immune to propaganda.


I agree, we should ban influencers from accepting any money from parties or other political actors (think tanks, foreign nations...). We can't and shouldn't ban them from expressing their honest opinions, but we should keep the debate genuine.


Influencers are a big problem indeed. The rules should be tightened quickly. Ads do work too, I'm afraid, so this is good


> People are not swayed by political ads.

That just means you are getting swayed, you just dont know it.


> People are not swayed by political ads

sure


Right? Who is that naive?


How come you think that said influencers are not paid?


As a world citizen, you're projecting. Most people are indeed swayed by political ads, as the numbers clearly bear out.


That's because you are a HN user, which selects for above average intelligence people (yes, even the webdevs). You are not the type of person who sways election results. Ads work. You don't need carefully crafted subliminal messages, you could write "vote for me" everywhere and it would have a noticeable effect on the election results


> That's because you are a HN user, which selects for above average intelligence people

This forum became a parody of itself


You may not like the way he put it, but he is correct.


Up to and including the snark at web devs. Every engineer I've met who thinks the web is somehow an easier form of software engineering couldn't write software worth a damn in general, let alone make a website. Universally incurious and dumb.


First-home buyers aren't the ones causing prices to go up.


New households absolutely are. Whether they choose to rent or buy is secondary.


It's REITs buying up housing for rental that drives up the pricing. There are serious social consequences to financializing basic needs.


> It's REITs buying up housing for rental that drives up the pricing

Almost certainly not. Institutional investors are too little of the market. And every time someone has seriously investigated this hypothesis, the evidence has been lacking.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: