Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI makes programming differently difficult

cacm.acm.org

Post reply on HN
Print view View original

141–150 of 154 posts

Re: AI makes programming differently difficult

#141

Post by runarberg »

CuriouslyC wrote: post #137
runarberg wrote: post #102

Earlier quoted context omitted.

That is simply not technologically possible. You are speaking in science fiction here. You cannot train a neural network on existing things and then by some magic have the model be better then the training data. The laws of statistics prohibit it.

For code you can do better than humans on a lot of metrics pretty easily bro. This is because you can RL on objective verified outputs. Kind of like how RL was used to make agents wipe the floor with humans in Dota2, chess and go. RLing taste and discernment are harder, but don't doubt that researchers can get a model that produces a more performant solution than you, while using less code, and being more secure/robu…

All your examples used little to no human created data and a very simple success criteria. LLMs on the other hand take massive amount of human created data (like almost all the human created data there is) and their success criteria is how well it predicts the next token. In other words, the success criteria of vibe coding models is how much it resembles the human created data. The more it resembles, the better the model.

Re: AI makes programming differently difficult

#142

Post by kypro »

sgarland wrote: post #124
kypro wrote: post #122

Earlier quoted context omitted.

> The problem is if you don’t understand the root cause, you’ll at best feed the LLM a list of symptoms Today maybe. When Cloudflare has an outage does the CEO need to know the root cause though? If he just assigns some engineers to investigate, fix and report back to him – what's the issue with that? Assuming you agree with my analogy, can you explain what it is that you feel an agent or group of agents assigned to…

My personal belief is that the most effective leaders do in fact deeply understand the technical side of their business, yes. To be fair, I am biased, because I was previously a nuclear reactor operator on a USN fast attack submarine, and the Commanding Officer is absolutely expected to fully understand technical issues. I think that a lot of organizational and technical problems would be solved if companies took sev…

> However, I don’t see a viable path forward where that occurs, and we all still have jobs. Why would I be kept around if a superhuman AI can do my job 1000x better and faster, and at a drastically cheaper price? Or, if I was kept around as a human QA agent, why would I be paid nearly what I am now?

Well as an AI doomer I agree with this. In my view you will lose your job, along with everyone else, and we'll just need to hope that those in power will give us some cash to feed our families. Ultimately us regular folks won't have the collective bargaining power of our labour and could not revolt with nation-wide strikes, nor are we any physical threat for those with power anymore.

But that's the good outcome. This assumes AI remains obedient to it's human owners and that bad actors don't have access and can't use it to create biological weapons and other civilisation-level threats.

I know we're not there yet, but the history of AI is one of continuous step changes in capabilities with each algorithmic breakthrough. AIs today are far more knowledgable and much quicker than humans, but still missing a few bits that keep them from being broadly super human. One or two algorithmic breakthroughs is all it takes though. It was just two breakthroughs over the last 8 years that took us from not even having code-autocomplete to having reasoning models advanced enough to solve math problems which have stumped humans for decades.

Re: AI makes programming differently difficult

#143

Post by sgarland »

kypro wrote: post #142
sgarland wrote: post #124

Earlier quoted context omitted.

My personal belief is that the most effective leaders do in fact deeply understand the technical side of their business, yes. To be fair, I am biased, because I was previously a nuclear reactor operator on a USN fast attack submarine, and the Commanding Officer is absolutely expected to fully understand technical issues. I think that a lot of organizational and technical problems would be solved if companies took sev…

> However, I don’t see a viable path forward where that occurs, and we all still have jobs. Why would I be kept around if a superhuman AI can do my job 1000x better and faster, and at a drastically cheaper price? Or, if I was kept around as a human QA agent, why would I be paid nearly what I am now? Well as an AI doomer I agree with this. In my view you will lose your job, along with everyone else, and we'll just nee…

> AIs today are far more knowledgable and much quicker than humans, but still missing a few bits that keep them from being broadly super human.

Generally, yes, but it’s the non-determinism that gets me. Even easy stuff: I’m currently on a road trip, and asked Claude (Fable) to plan various routes, optimizing for scenery while also ensuring a maximum drive time each day, and ending every night in a town that has a decent hotel. Along the way, I’ve made various tweaks, like “we’d like to drive an extra hour or two today, so adjust the rest of the route so we don’t end up with a short intermediate day.” While in general it’s done quite well, it occasionally made errors on distance between stops, something that’s trivially queryable. It wasn’t off by a few miles, either, it was hundreds.

Until they can get the confidently incorrect problem solved, I don’t see it being a viable replacement. Maybe if you have agents that are aggressively checking the main ones’ output, but that seems unnecessarily wasteful of resources to me.

Re: AI makes programming differently difficult

#144

Post by reinitctxoffset »

gatio wrote: post #133
reinitctxoffset wrote: post #103

Earlier quoted context omitted.

I think it's easier to make your point without the baggage of the mechanism assertions. The code is just wrong a lot. By denying the possibility of emergent phenomemona or model interiority you just hand the hypsters an easy point to score. The code is just wrong, all the time. You're right about the part that matters and that we can measure.

Except... it does produce solid code in many scenarios. A lot of the time we are just applying the same patterns and tools to a specific problem. If you understand the problem, agents can and are producing quality code. I do a lot with orchestrating cloud infra, provisioning and deprovisioning workflows, lifecycle management, updating CMDBs, access management, deployment automation, auditing configurations, and some…

it does do good code sometimes. it does both. we're trying to figure out how to net that out to good overall. right now it's a bit tricky because we didn't build our world for the code to be really good and then disasterously bad all the sudden and then good for a while again and it seems like someone is programming a slot machine.

这波

Re: AI makes programming differently difficult

#145

Post by gwbas1c »

nasretdinov wrote: post #74

Definitely not my experience. No matter the model, if I'm working on something important (and there is little reason on working on something not important) I do care about correctness and understandability. While LLMs are great for throwaway one-time code (although that's also debatable), they cannot compete with code written by a seasoned professional. No matter how many times I've tried delegating writing code to L…

Some things to consider:

1: The quality of code varies widely from model to model. In Visual Studio Copilot, I get so-so code from GPT, great code from Claude 4.x, lousy results from Claude 5.x

2: "Novel work" is harder to get from an LLM than when it's following an example. For example, I can get great Blazor / HTML / css from an LLM (and then spend time iterating making small adjustments,) but if I'm writing a complicated DB query or implementing a novel algorithm, it's best to do by hand.

3: But, in the case of a novel algorithm or query, I get great results saying "please write unit tests for XXX". That alone makes me develop code twice as fast!

Re: AI makes programming differently difficult

#146

Post by AnimalMuppet »

bluefirebrand wrote: post #120
dsmurrell wrote: post #6

It's somehow more tiring, reading complex plans in response to your guidance, and then making decision after decision. Reminds me of this Alan Watts bit... A farmer who ordered a farmhand quickly discovered he was an extraordinarily efficient worker. The first day, he put him on sawing logs, and the farmhand sawed more logs than anybody else, ever. It was fantastic — but the wood-cutting work was all done in one day.…

For me, the stress about making decisions as an employee isn't about making a choice. It's knowing that any moment a manager is going to wander along and change it from under me. So I might as well ask the manager first. It showed up on my performance reviews that I'm bothering other people with questions and I should make my own choices, so I started doing that and documenting every time the choice I made got overtu…

But for me to be able to make decision after decision, I need to know what the over-riding guidelines are. I need to know what we're trying to build, and know it well enough that I know how my part fits.

And then I need to be able to tell when I can make a decision, and when I don't have enough information to make that decision and therefore need to ask questions of someone who has a better handle on the overall picture.

Re: AI makes programming differently difficult

#147

Post by kypro »

sgarland wrote: post #143
kypro wrote: post #142

Earlier quoted context omitted.

> However, I don’t see a viable path forward where that occurs, and we all still have jobs. Why would I be kept around if a superhuman AI can do my job 1000x better and faster, and at a drastically cheaper price? Or, if I was kept around as a human QA agent, why would I be paid nearly what I am now? Well as an AI doomer I agree with this. In my view you will lose your job, along with everyone else, and we'll just nee…

> AIs today are far more knowledgable and much quicker than humans, but still missing a few bits that keep them from being broadly super human. Generally, yes, but it’s the non-determinism that gets me. Even easy stuff: I’m currently on a road trip, and asked Claude (Fable) to plan various routes, optimizing for scenery while also ensuring a maximum drive time each day, and ending every night in a town that has a dec…

> Until they can get the confidently incorrect problem solved, I don’t see it being a viable replacement. Maybe if you have agents that are aggressively checking the main ones’ output, but that seems unnecessarily wasteful of resources to me.

2 years ago AI could even count the number of letters in a word or do basic maths. Now we're at the point where we can't trust it because makes occasional errors.

Don't get me wrong, I agree with you. These are things that need to be solved first, I just don't have reason to believe these are particularly difficult problems.

Anyway, I enjoyed the convo. Was interesting hearing your thoughts. I would give anything to be wrong.

Re: AI makes programming differently difficult

#148

Post by m3kw9 »

bluefirebrand wrote: post #119
m3kw9 wrote: post #97

Earlier quoted context omitted.

double edge sword of LLM code generation, you cannot catch 100%, nor do you want to always ready every single word. Gotta develop a feel.

Engineering by feels... Is this what we've come to?

Yes, feel, not your type of feel, my type where you can scan a section and know it's this architecture, compartmentized, know the general performance impact. Yes.

Re: AI makes programming differently difficult

#149

Post by agumonkey »

zombot wrote: post #135
agumonkey wrote: post #50

Earlier quoted context omitted.

Yes a LLM is mostly an information memory de vice, but as a worker you still have to vet it. I believe the human constraint made us find ways to layer and modularize systems so it is easier to check. Now the LLM produces a lot of code and abstraction have to be enforced. Something is missing.. (resonates with the latest Pocoo blog)

What is "de vice" supposed to mean?

smartphone typo, i meant 'device'
Post reply on HN