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

I'm going back to writing code by hand

blog.k10s.dev

Post reply on HN
Print view View original

331–340 of 656 posts

Re: I'm going back to writing code by hand

#331

Post by wolttam »

djeastm wrote: post #275

When it was Copilot tab-completing lines, people would say, "yea, but you still have to make sure you're the one writing the whole functions". Then when it was completing functions, people would say, "yeah, but you still have to make sure you're the one writing the logic around the functions" Then when it was completing the logic around the functions, people would say, "yeah, but you still have to make sure you're th…

These models understand architecture perfectly well, but they're not trained to care about it when being asked to complex X or Y feature. They're trained to implement the feature in the shortest route possible.

So it's not much of a surprise that this is the situation folks find themselves in with the current models.

Re: I'm going back to writing code by hand

#332

Post by estearum »

bigfishrunning wrote: post #309
herdcall wrote: post #306

Earlier quoted context omitted.

I'm no longer sure you have to, actually. I mean, we do trust the assembly that compilers produce without having to read it, don't we? We're rapidly getting to that stage with LLMs, IMO.

The assembly is a deterministic transform of the input logic, and if it doesn't match then it's a bug in the compiler. If an LLM-based code generator doesn't match what you asked for, that's OK, just pull the slot-machine handle again. that's the difference.

For now, but obviously they're becoming (effectively) more and more similar to the former every day.

Re: I'm going back to writing code by hand

#333

Post by yakattak »

herdcall wrote: post #306
raincole wrote: post #290

Earlier quoted context omitted.

The "people" in your hypothetical story have been wrong the whole time. The correct attitude is: When AI can complete lines, you still have to read and understand the code. When AI can complete whole functions, you still have to read and understand the code. When AI can complete features and tickets, you still have to read and understand the code.

I'm no longer sure you have to, actually. I mean, we do trust the assembly that compilers produce without having to read it, don't we? We're rapidly getting to that stage with LLMs, IMO.

I want to preface this with that I am all for agentic engineering.

I am so tired of hearing about this false equivalency. Compilers are deterministic, their outputs are well understood and they’re transparent.

LLMs are not.

Re: I'm going back to writing code by hand

#334

Post by dzhiurgis »

gritzko wrote: post #172
dzhiurgis wrote: post #124

Earlier quoted context omitted.

That’s why I love gemini - none of this bullshit ever happen.

I do not think Gemini can relieve a developer from knowing what he is doing.

No but it can actually go a fix a bug instead of disabling unit test..?

Re: I'm going back to writing code by hand

#335

Post by Xunjin »

bigfishrunning wrote: post #309
herdcall wrote: post #306

Earlier quoted context omitted.

I'm no longer sure you have to, actually. I mean, we do trust the assembly that compilers produce without having to read it, don't we? We're rapidly getting to that stage with LLMs, IMO.

The assembly is a deterministic transform of the input logic, and if it doesn't match then it's a bug in the compiler. If an LLM-based code generator doesn't match what you asked for, that's OK, just pull the slot-machine handle again. that's the difference.

Thank you for this, people often miss the point, comparing apples with oranges.

Re: I'm going back to writing code by hand

#336

Post by dzhiurgis »

2ndorderthought wrote: post #205
gritzko wrote: post #172

Earlier quoted context omitted.

I do not think Gemini can relieve a developer from knowing what he is doing.

There's some really weird and unusual posts glazing Google in here today. Bot accounts out in force!

Says 27 day old account

Re: I'm going back to writing code by hand

#337

Post by agentultra »

pron wrote: post #325
agentultra wrote: post #300

Earlier quoted context omitted.

The invariant, stated informally, would be hard to prove is broken by a human reviewer in the loop. Spoken language isn’t precise enough for the task. Even if you could state it in a precise formal language the LLM under the agent doesn’t have the capability to understand what the invariant is for and why it’s important. You’ll still get oddly generated code. You might get an LLM that can associate certain tokens wit…

> The invariant, stated informally, would be hard to prove is broken by a human reviewer in the loop. Spoken language isn’t precise enough for the task. That depends on the invariant. Some are behavioural, like "variable x must be even if y is positive", but some are architectural, such as "a new view requires a new class". But that's only one side of the problem because maintaining the invariant can be just as bad a…

Yes! I was trying to make this part of my point but you definitely made it much more clear and concise.

With a skilled operator, it could be possible to drive an agent to handle these kinds of changes. I would be concerned that spoken language wouldn't be precise enough to handle the refactoring and changes necessary to make to a code base when an invariant changes... regardless of whether it was a property, architectural, or procedural change. It already can take several prompts and burn quite a few tokens doing large-scale rewrites and code changes. Maybe the parameters and weights can be tuned for this kind of work but I remain skeptical that what we have at present is "efficient" at this kind of work.

Re: I'm going back to writing code by hand

#338

Post by fancythat »

echelon wrote: post #216
20k wrote: post #151

I always find these kinds of posts interesting, to compare the velocity that people seem to get with Ai, vs what I get by just coding by hand Coincidentally I've been working on a project for about 7 months now: its a 3d MMO. Currently its playable, and people are having fun with it - it has decent (but needs work) graphics, and you can cram a few hundred people into the server easily currently. The architecture is p…

This was made in two days of vibe coding. It has flaws, but it's impressive as hell: https://tinyskies.vercel.app/ It's got a fun Zelda-inspired mechanic (I won't say which one), and you'll have to unlock abilities and parts of the world over several quests and modes to "win". It's also multiplayer.

Unless there is a way to see or check the whole prompt that made this game, it is hard for me personally to say if this is impressive or not as I don't know what percentage of this was vibe coded. I also see there is an incentive to skew the truth here, as there is a substantial prize pool and that usually makes people become very creative.

In the past, I was trying to reproduce vibe coding results when I managed to get all the information from Youtube videos (model version, ide version, same input data and prompt) and never was I able to reproduce something impressive even after multiple runs of the same thing.

Re: I'm going back to writing code by hand

#340

Post by linuxftw »

pron wrote: post #192

Yep. The only people I've heard saying that generated code is fine are those who don't read it. The problem is that the mitigations offered in the article also don't work for long. When designing a system or a component we have ideas that form invariants. Sometimes the invariant is big, like a certain grand architecture, and sometimes it’s small, like the selection of a data structure. You can tell the agent what the…

Try plan mode. The problems you're speaking about are already solved.
Post reply on HN