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

After months of coding with LLMs, I'm going back to using my brain

albertofortin.com

Post reply on HN
Print view View original

221–229 of 229 posts

Re: After months of coding with LLMs, I'm going back to using my brain

#221

Post by CuriouslyC »

fragmede wrote: post #217
WD-42 wrote: post #170

Earlier quoted context omitted.

This shows nothing.

Maybe better formatting would show it better to you. github.com/AlDanial/cloc v 2.04 T=0.05 s (666.3 files/s, 187924.3 lines/s) ---- Language files blank comment code ---- Python 24 1505 1968 5001 ---- Markdown 4 37 0 121 ---- Jinja Template 3 17 2 92 ------------- SUM: 31 1559 1970 5214

I wouldn't waste your time, if someone wants to stick their head in the sand rather than reconsider what's possible because it personally threatens their ego and world view, nothing's going to change their mind. If I were to share the code he'd probably grasp at smoke trying to find ways to discredit it rather than try to understand my workflow and replicate my results.

Re: After months of coding with LLMs, I'm going back to using my brain

#222

Post by WD-42 »

CuriouslyC wrote: post #221
fragmede wrote: post #217

Earlier quoted context omitted.

Maybe better formatting would show it better to you. github.com/AlDanial/cloc v 2.04 T=0.05 s (666.3 files/s, 187924.3 lines/s) ---- Language files blank comment code ---- Python 24 1505 1968 5001 ---- Markdown 4 37 0 121 ---- Jinja Template 3 17 2 92 ------------- SUM: 31 1559 1970 5214

I wouldn't waste your time, if someone wants to stick their head in the sand rather than reconsider what's possible because it personally threatens their ego and world view, nothing's going to change their mind. If I were to share the code he'd probably grasp at smoke trying to find ways to discredit it rather than try to understand my workflow and replicate my results.

I use AI every day. But 5-10k loc is a huge claim, ai or not. It’s just too bad you can’t back it up - nobody ever can because sorry “closed source” (ironic considering these llms having been trained on open source…) Let me guess, it’s an AI product?

Re: After months of coding with LLMs, I'm going back to using my brain

#223

Post by Too »

kragen wrote: post #169
meander_water wrote: post #65

The thing most LLM maximalists don't realize is that the bottleneck for most people is not code generation, it's code understanding. You may have doubled the speed at which you created something, but you need to pay double that time back in code review, testing and building a mental model of the codebase in your head. And you _need_ to do this if you want to have any chance of maintaining the codebase (i.e. bugfixes,…

I've found LLMs are pretty good at explaining my code back to me.

That will only work for the most simple of functions. How would you even make such a prompt? "Plz explain this code for me?" It's going to come back with the same essential complexity except in English instead of Javascript, you still need to understand the surroundings. Often you need to approach the understanding from different angles. Are you going to ask it "What will happen given preconditions A, B and C". How many of those questions do you need?

Not to mention how slow this is, instead of just reading a piece of code or instantly query my already existing internal mental model of it, I have to type a prompt, wait for the response, read the response, hope it understood my intent, hope it understood the code, map it to my own understanding.

Re: After months of coding with LLMs, I'm going back to using my brain

#224

Post by jeromystewart1 »

In order to convey all of the ways that Gemini, Claude, O4-mini and many other LLMs have worked aggressively to sabotage my systems would take an unreasonable amount of time to describe. Among the more ridiculous occurrences have been actively ignoring instructions to read my comprehensive docs, the system spec and coding principles documents. These LLMs will rewrite your architecture when you have only provided an instruction to make a simple change. The fact that some individuals are supposedly experiencing LLM euphoria leads me to one conclusion. They aren't producing anything that is complex and they probably don't have a large codebase. Furthermore, I wonder if the so-called vibe coders are actually looking at and understanding the code at all.

Re: After months of coding with LLMs, I'm going back to using my brain

#225

Post by CuriouslyC »

WD-42 wrote: post #222
CuriouslyC wrote: post #221

Earlier quoted context omitted.

I wouldn't waste your time, if someone wants to stick their head in the sand rather than reconsider what's possible because it personally threatens their ego and world view, nothing's going to change their mind. If I were to share the code he'd probably grasp at smoke trying to find ways to discredit it rather than try to understand my workflow and replicate my results.

I use AI every day. But 5-10k loc is a huge claim, ai or not. It’s just too bad you can’t back it up - nobody ever can because sorry “closed source” (ironic considering these llms having been trained on open source…) Let me guess, it’s an AI product?

Nope, it's an internal company tool to build high performance distributable container images based on a manifest of services for resource constrained edge devices with an installer that manages installing, configuring, removing, auto-updating and daemonizing the container process across a variety of OS targets.

The container images also have significant logic for interfacing securely with the private company network and upstream services given on-prem or edge deployment.

Re: After months of coding with LLMs, I'm going back to using my brain

#226

Post by iser_ »

jwblackwell wrote: post #130

> the current PHP+MySQL combo was not fit for purpose anymore He lost me here. Sounds like he tried to change from a boring stack he understood, to Go and Clickhouse because it's cooler. You're asking for trouble. LLMs are great and getting better, but you can't expect them to handle something like this right now

he needed an OLAP db, not OLTP, makes perfect sense to me...

Re: After months of coding with LLMs, I'm going back to using my brain

#227

Post by andrekandre »

diggan wrote: post #214
andrekandre wrote: post #207

Earlier quoted context omitted.

> ExpertSexchange maybe should have added a space somewhere in there?

I thought explicitly using wrong caps would be enough for most people to get it regardless :)

it gave me a chuckle regardless lol

Re: After months of coding with LLMs, I'm going back to using my brain

#228

Post by kragen »

Too wrote: post #223
kragen wrote: post #169

Earlier quoted context omitted.

I've found LLMs are pretty good at explaining my code back to me.

That will only work for the most simple of functions. How would you even make such a prompt? "Plz explain this code for me?" It's going to come back with the same essential complexity except in English instead of Javascript, you still need to understand the surroundings. Often you need to approach the understanding from different angles. Are you going to ask it "What will happen given preconditions A, B and C". How m…

That isn't my experience at all.

Re: After months of coding with LLMs, I'm going back to using my brain

#229

Post by miketromba »

Oof this is a very limited take.

The fundamental issue is that agents / LLMs at present are not engineers or system architects. You cannot sit back and play product manager yet. If you go in with this expectation, you will certainly have a poor experience.

LLM-powered coding agents are not comparable to any existing human role or tool and therefore cannot be used interchangeably. They are a fundamentally new and novel type of tool that enable incredible productivity IF and only if you use them effectively. The tool is not the problem, the user is.

I’m also building a non-trivial SaaS platform and the cursor agent has written 90%+ of the code in the codebase. It has architected ~0% of the codebase. It has modeled ~0% of the data layer in the codebase. It has enabled me to move at least 10x the speed of implementation and debugging (yes, it is incredible at debugging if you use the right techniques).

I use the word implementation because that is almost exclusively what I use it for. I do the planning, design, architecture, engineering. Then, I communicate those specifications to it in digestible chunks, and it implements them incredibly fast. It makes mistakes sometimes, comes up with poor naming conventions, fails to reuse existing modules in the codebase, etc. But that’s fine - I simply give it feedback, point it in the right direction, and within seconds it’s back on course.

I own the codebase, it’s just my super fast implementation minion. If it gets something wrong - that’s my fault. I failed to communicate my expectations clearly. I’m heavily using my brain while working with the LLM - I’m just reserving those mental cycles for higher-level decision making than the actual tokens to type into the editor.

The power is in your ability to steer it and communicate in clear terms what you want, and maintain the right level of abstraction in your instructions. Too specific and you lose some of the benefit beyond just writing the code by hand, too vague / high-level and it will over-engineer something totally different than what you intended.

You’re the engineer, it’s just a really smart semantic code generator. That might change in the future, but for now, if you use it in this way, the productivity benefit is very clear.

I’ve been using cursor with 3.7 sonnet max (now sonnet 4) and I already can’t imagine a world without coding agents - it is so deeply rooted into my workflow.

Post reply on HN