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

How I program with agents

crawshaw.io

Post reply on HN
Print view View original

251–260 of 308 posts

Re: How I program with agents

#251

Post by aryehof »

bicepjai wrote: post #248
quantumHazer wrote: post #2

Finally some serious writing about LLMs that doesn’t follow the hype and it faces reality of what can and can’t be useful with these tools. Really interesting read, although I can’t stand the word “agent” for a for-loop that call recursively an LLM, but this industry is not famous for being sharp with naming things, so here we are. edit: grammar

I liked the phrase “tools in a loop” for agents. I think Simon said that

He was quoting someone else. Please take care not to attribute falsely, as it creates a falsehood likely to spread and become the new (un) truth.

Re: How I program with agents

#252

Post by solatic »

munificent wrote: post #179
marvstazar wrote: post #103

Earlier quoted context omitted.

As a senior developer you already spend a significant amount of time planning new feature implementations and reviewing other people's code (PRs). I find that this skill transitions quite nicely to working with coding agents.

I don't disagree but... wouldn't you rather be working with actual people? Spending the whole day chatting with AI agents sounds like a worst-of-both-worlds scenarios. I have to bring all of my complex, subtle soft skills into play which are difficult and tiring to use, and in the end none of that went towards actually fostering real relationships with real people. At the end of the day, are you gonna have a beer wit…

It's a double-edged sword. AI agents don't have a long-term context window that gets better over time. People who employ AI agents today instead of juniors are going to find themselves in another local maximum: yes, the AI agent will make you more productive today compared to a junior, but (as the tech stands today) you will never be able to promote an AI agent to senior or staff, and you will not get to hire out an army of thousands of engineers that lets you deliver the sheer throughput that FAANG / Fortune 500 are capable of. You will be stuck at some shorter level of feature-delivery capacity.

Re: How I program with agents

#253

Post by j1436go »

vmg12 wrote: post #13
zOneLetter wrote: post #7

Maybe it's because I only code for my own tools, but I still don't understand the benefit of relying on someone/something else to write your code and then reading it, understand it, fixing it, etc. Although asking an LLM to extract and find the thing I'm looking for in an API Doc is super useful and time saving. To me, it's not even about how good these LLMs get in the future. I just don't like reading other people's…

Here are the cases where it helps me (I promise this isn't ai generated even though im using a list...) - Formulaic code. It basically obviates the need for macros / code gen. The downside is that they are slower and you can't just update the macro and re-generate. The upside is it works for code that is slightly formulaic but has some slight differences across implementations that make macros impossible to use. - Us…

As a personal anecdote I've tried to create Shell scripts for the testing of a public HTTP API that had pretty good documentation and in both cases the requests did not work. In one case it even hallucinated an endpoint.

Re: How I program with agents

#254

Post by aryehof »

quantumHazer wrote: post #2

Finally some serious writing about LLMs that doesn’t follow the hype and it faces reality of what can and can’t be useful with these tools. Really interesting read, although I can’t stand the word “agent” for a for-loop that call recursively an LLM, but this industry is not famous for being sharp with naming things, so here we are. edit: grammar

I agree with not liking the author’s definition of an Agent being … “a for loop which contains an LLM call”.

Instead it is an LLM calling tools/resources in a loop. The difference is subtle and a question of what is in charge.

Re: How I program with agents

#255

Post by crazylogger »

therein wrote: post #147
danielbln wrote: post #126

Earlier quoted context omitted.

What is an essential tool? IDE? Editor? Pencil? Can I scratch my code into a French cave wall if I want to be a senior developer?

I think it is very simple to draw the line at "something that tries to write for you", you know, an agent by definition. I am beginning to realize people simply would prefer to manage, even if the things they end up managing aren't actually humans. So it creates a nice live action role-play situation. A better name for vibecoding would be larpcoding, because you are doing a live action role-play of managing a staff o…

It’s not a clear line though. Compilers have been writing programs for us. The plaintext programming language code that we talk about is but a spec for the actual program.

From this perspective, English-as-spec is a natural progression in the direction we’ve been going all along.

Re: How I program with agents

#256

Post by gf000 »

csallen wrote: post #156
dingnuts wrote: post #146

Earlier quoted context omitted.

The difference is that humans learn. I got bit by this behavior of CombinedOutput once ten years ago, and no longer make this mistake.

This applies to AI, too, albeit in different ways: 1. You can iteratively improve the rules and prompts you give to the AI when coding. I do this a lot. My process is constantly improving, and the AI makes fewer mistakes as a result. 2. AI models get smarter. Just in the past few months, the LLMs I use to code are making significantly fewer mistakes than they were.

But my gripe with your first point is that by the time I write an exact detailed step-by-step prompt for them, I could have written the code by hand. Like there is a reason we are not using fuzzy human language in math/coding, it is ambiguous. I always feel like doing those funny videos where you have to write exact instructions on how to make a peanut butter sandwich, getting deliberately misinterpreted. Except it is not fun at all when you are the one writing the instructions.

2. It's very questionable that they will get any smarter, we have hit the plateau of diminishing returns. They will get more optimized, we can run them more times with more context (e.g. chain of thought), but they fundamentally won't get better at reasoning.

Re: How I program with agents

#257

Post by gyomu »

djeastm wrote: post #196
gyomu wrote: post #168

Earlier quoted context omitted.

> I’m driving a tractor while you are pulling an ox cart. Or you’re assembling prefab plywood homes while they’re building marble mansions. It’s easy to pick metaphors that fit your preferred narrative :)

>you’re assembling prefab plywood homes while they’re building marble mansions Which one are there more of nowadays, hm?

Maybe the least interesting question to ask. Instead: Which ones are more lucrative to work on? Which ones are more fun to work on?

Re: How I program with agents

#258

Post by KronisLV »

zOneLetter wrote: post #7

Maybe it's because I only code for my own tools, but I still don't understand the benefit of relying on someone/something else to write your code and then reading it, understand it, fixing it, etc. Although asking an LLM to extract and find the thing I'm looking for in an API Doc is super useful and time saving. To me, it's not even about how good these LLMs get in the future. I just don't like reading other people's…

> I still don't understand the benefit of relying on someone/something else to write your code and then reading it, understand it, fixing it, etc.

Friction.

A lot of people are bad at getting started (like writer's block, just with code), whereas if you're given a solution for a problem, then you can tweak it, refactor it and alter it in other ways for your needs, without getting too caught up in your head about how to write the thing in the first place. Same with how many of my colleagues have expressed that getting started on a new project from 0 is difficult, because you also need to setup the toolchain and bootstrap a whole app/service/project, very similar to also introducing a new abstraction/mechanism in an existing codebase.

Plus, with LLMs being able to process a lot of data quickly, assuming you have enough context size and money/resources to use that, it can run through your codebase in more detail and notice things that you might now, like: "Oh hey, there are already two audit mechanisms in the codebase in classes Foo and Bar, we might extract the common logic and..." that you'd miss on your own.

Re: How I program with agents

#259

Post by gf000 »

Groxx wrote: post #75
vmg12 wrote: post #28

Earlier quoted context omitted.

There is a lot of formulaic code that llms get right 90% of the time that are impossible to build macros for. One example that I've had to deal with is language bridge code for an embedded scripting language. Every function I want available in the scripting environment requires what is essentially a boiler plate function to be written and I had to write a lot of them.

There's also fuzzy datatype mapping in general, where they're like 90%+ identical but the remaining fields need minor special handling. Building a generator capable of handling all variations you might need is extremely hard[1], and it still won't be good enough. An LLM will both get it almost perfect almost every time, and likely reuses your existing utility funcs. It can save you from typing out hundreds of lines,…

Well yeah, this is a good application of LLMs as this is a fundamentally text-to-text operation they excel at.

But then why are so many people expect them to do well in actual reasoning tasks?

Re: How I program with agents

#260

Post by gf000 »

owebmaster wrote: post #223
pineaux wrote: post #133

Earlier quoted context omitted.

I have always found this idea of not being smarter somewhat baffling. Education makes people smarter does it not? At least that is one of the claims it makes. Do you mean that a baby hunter gatherer from 25000 years ago would be on average just as capable of learning stuff when integrated into society compared to someone born nowadays? For human beings 25.000 years is something like 1000 generations. There will be su…

what if we actually get dumber? There are multiple cases of people in the past that are way smarter than the current thought leaders and inventors. There are a higher % of smart people nowadays but are they smarter than Leonardo Da Vinci?

You are just looking at the wrong people to compare.

Leonardo Da Vinci would be a PhD student working on some obscure sub-sub-sub field of something and only 6 other people on the world understanding how marvelously genius he is. The reason they don't get to such a status is that human knowledge is like a circle. A single person can work on the circumference of this circle, but they are limited by what they can learn of this circle. As society improved, we have expanded the radius of the circle greatly, and now an expert can only be an expert in a tiny tiny blob on the circumference, while Leonardo could "see" a good chunk of the whole circle.

---

"Thought leader and inventor" are VC terms of no substance and are 100% not who I would consider smart people on average. Luck is a much more common attribute among them.

Post reply on HN