Https://Sketch.dev is incredible. It immediately solved a task that Google Jules failed several times to do. Thanks David!
curious, what (type of) task?
How I program with agents
291–300 of 308 posts
Re: How I program with agents
#292Earlier quoted context omitted.
Amusingly, cursor took 5 minutes trying to figure out how to do what a simple global find/replace did for me in 30 seconds after I got tired of waiting for it's attempt just last night on a simple predictable lots-of-files change. A 60x speedup is way more than I've seen even in its best case for things like that.
In my experience, two things makes a big difference for AI agents: quality of code (naming and structure mostly) and AI-friendly documentation and tasks planning. For example, in some repos I have legacy naming that evolved after some refactoring, and while devs know that "X means Y", it's not easy for AI to figure it out unless explicitly documented. I'm still learning how to organize AI-oriented codebase documentat…
This was "I want to update all the imports to the new version of the library, where they changed a bit in the fully qualified package name." Should be a super-trivial change for the AI agent to understand.
Like I mentioned, it's literally just global find and replace.
Slightly embarrassing thing to have even asked Cursor to do for me, in retrospect. But, you know, you get used to the tool and to being lazy.
Re: How I program with agents
#293I think what AI "should" be good at is writing code that passes unit-tests written by me the Human. AI cannot know what we want it to write - unless we tell it exactly what we want by writing some unit-tests and tell it we want code that passes them. But is any LLM able to do that?
You can write the tests first and tell the AI to do the implementation and give it some guidance. I usually go the other direction though, I tell the LLM to stub the tests out and let me fill in the details.
Re: How I program with agents
#294Maybe 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…
You’re clinging to an old model of work. Today an LLM converted my docker compose infrastructure to Kubernetes, using operators and helm charts as needed. It did in 10 minutes what would take me several days to learn and cobble together a bad solution. I review every small update and correct it when needed. It is so much more productive. I’m driving a tractor while you are pulling an ox cart.
I think this fits squarely with the idea that LLM today is a great learning tool; learning through practice has always been a proven way to learn but a difficult method to learn from fixed material like books.
LLM is a teacher that can help you learn by doing the work you want to be doing and not some fake exercise.
The more you learn though, the more you review the code produced by the LLM and the more you'll notice that you are still able to reason better than an LLM and after your familiarity with an area exceeds the capabilities of the LLM the interaction with the LLM will bring diminishing returns and possibly the cost of babysitting that eager junior developer assistant may become larger than the benefits.
But that's not a problem, for all areas you master there will be hundreds of other areas you haven't mastered yet or ever will and for those things the LLM we have already today are of immediate help.
All this without even having to enter the topic of how coding assistants will improve in the future.
TL;DR
Use a tool when it helps. Don't use it when it doesn't. It pays to learn to use a tool so you know when it helps and when it doesn't. Just like every other tool
Re: How I program with agents
#295Earlier quoted context omitted.
You are moving goalposts significantly here -- a small CSS hack is a far cry from your docker infrastructure.
I am going to put it out here: Docker and other modern infra is easier to understand than CSS (at least pre flex).
My take from this comment is that maybe you do not understand it as well as you think you do.
Claiming that "other modern infrastructure" is easier to understand than CSS is wild to me. Infrastructure includes networking and several protocol, authentication and security in many ways, physical or virtual resources and their respective capabilities, etc etc etc.
In what world is all of that more easy than understanding CSS?
Re: How I program with agents
#296Earlier quoted context omitted.
My house has never been cleaner. I have time to catch up on chores that I normally do during the weekend. Dishes, laundry, walk the dog more. It seems silly but it’s opened up a lot of extra time for some of this stuff. Heck, I even play my guitar more, something I’ve neglected for years. Noodle around while I wait for Claude to finish something and then I review it. All in all, I dig this new world. But I also code…
That doesn't sound like a situation that will last. If management figures out you are using this extra time to do all your chores, they aren't gonna reward you. They might decide to get someone who would use the extra time to do more work...
So much of what people hyping AI write in this forums boils down to "this vendor will keep making this tool better forever and management will let me keep the productivity gains".
Experience shows otherwise. Urging me to embrace a new way of building software that is predicated on benevolent vendors and management seems hostile to me.
Re: How I program with agents
#297Earlier quoted context omitted.
What’s not clear to me is how agents/AI written code solves the “half hearted review” problem. People don’t like to do code reviews because it sucks. It’s tedious and boring. I genuinely hope that we’re not giving up the fun parts of software, writing code, and in exchange getting a mountain of code to read and review instead.
Yes, this is what I'm fearing as well. That we will end up just trying to review code, writing tests and some kind of specifications in natural language (which is very imprecise) However, I can't see how this approach would ever scale to a larger project.
This is an attempt to change software development from a put out system to a factory system.
It seems to be working sadly. If people hated agile, just wait for the prompt/code review sweatshops.
Re: How I program with agents
#298I wonder how many people that use agents actually like "programming", as in coming up with a solution to the problem and then being able to express that in code. It seems like a lot of the work that the agents are doing is removing that and instead making you have to explain what you want in natural language and hope the LLM doesn't introduce bugs
Most coders prefer to throw code at the wall and see what sticks. These tools are a gas-powered catapult.
I don't think anyone is wrong, I am not here to detract from this. I just think most people want things that are very different than what I want.
Re: How I program with agents
#299Finally 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 saw a LinkedIn post (I know, I know) talking about how soon agents will replace apps. . .
Because of course, LLM calls in a for loop are also not applications anymore.
Re: How I program with agents
#300Earlier quoted context omitted.
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.
You are right.
During a “Prompting for Agents” workshop at an Anthropic developer conference, Hannah Moran described agents as “models using tools in a loop.”