321–330 of 396 posts
Earlier quoted context omitted.
So what use is it to filter them? It seems you still have to judge their worth based on their actual contents.
Consider there are 100 upvotes and 100 downvotes. Net votes: 0. The submission would end up with a lower ranking that you wanted it to have.
After working with the latest models I think these "it's just another tool" or "another layer of abstraction" or "I'm just building at a different level" kind of arguments are wishful thinking. You're not going to be a designer writing blueprints for a series of workers to execute on, you're barely going to be a product manager translating business requirements into a technical specification before AI closes that gap…
If all you (not you specifically, more of a royal “you” or “we”) are is a collection of skills centered around putting code into an editor and opening pull requests as fast as possible, then sure, you might be cooked. But if your job depends on taste, design, intuition, sociability, judgement, coaching, inspiring, explaining, or empathy in the context of using technology to solve human problems, you’ll be fine. The p…
Earlier quoted context omitted.
This claim has been going around for a while. I know someone who has been spending $7k / month on Cursor tokens for the past six months, managing such a team of agents… But curiously the results seem to be endless PDF-ware, and every month there’s a new reason why the project is not yet quite ready to be used on real data. LLMs are very good at making you think they’re giving you what you hoped to get.
They're also very good at demoralizing people who actually code for a living. Or at least the hype surrounding them is. Up until a couple years ago I'd simply dive into a new coding assignment and be excited to solve all the problems. Some new widget? Maybe I could find a way to make the UX flow better, or add a couple neat little transitions, or heck even improve the mechanics or the business logic. I now find mysel…
At job, we have a lot of internal web apps coded like hell : "people just have to reload the page ..": this is lame
On the other hand, on many situations, when people are faced with something that works, that is well designed and well executed, it's a breath of fresh air and they do notice and they do note that "that team is not like the others" (even if they cannot always pinpoint the "why")
High quality work also leads to higher velocity, low/no regressions etc
Management does notice, product owner do notice
Earlier quoted context omitted.
English can be ambiguous. Programming languages like C or Java cannot
English CAN be ambiguous, but it doesn't have to be. Think about it. Human beings are able to work out ambiguity when it arrises between people with enough time and dedication, and how do they do it? They use English (or another equivalent human language). With enough back and forth, clarifying questions, or enough specificity in the words you choose, you can resolve any ambiguity. Or, think about it this way. In ord…
Programming languages are written to eliminate that ambiguity because you don't want your bank server to make a payment because it misinterpreted ambiguous language in the same way that you might misinterpret your spouse's remarks.
Can that ambiguity be resolved with more English words? Maybe. But that would require humans to be perfect communicators, which is not that easy because again, if it were possible, humans would have learnt to first communicate perfectly with the people closest to them.
Earlier quoted context omitted.
There are definitely issues in human software engineering which reach some combination of the following end states: 1. The team is unable to figure it out 2. The team is able to figure it out but a responsible third-party dependency is unable to fix it 3. The team throws in the towel and works around the issue At the end of the day it always comes down to money: how much more money do we throw at trying to diagnose o…
> I don't see why this would ipso facto be different with AI Because humans can learn information they currently do not have, AI cannot?
That doesn't mean AI can do or replace everything but what fraction of software engineering work requires that final frontier?
If we consider the prompts and LLM inputs to be the new source code, I want to see some assurance we get the same results every time. A traditional compiler will produce a program that behaves the same way, given the same source and options. Some even go out of their way to guarantee they produce the same binary output, which is a good thing for security and package management. That is why we don't need to store the…
> I want to see some assurance we get the same results every time Genuine question, but why not set the temperature to 0? I do this for non-code related inference when I want the same response to a prompt each time.
Earlier quoted context omitted.
I'm not sure I'd call agents an army of juniors. More like a high school summer intern who has infinite time to do deep dives into StackOverflow but doesn't have nearly enough programming experience yet to have developed a "taste" for good code In my experience, agentic LLMs tend to write code that is very branchy with cyclomatic complexity. They don't follow DRY principles unless you push them very hard in that dire…
> In my experience, agentic LLMs tend to write code that is very branchy with cyclomatic complexity You are missing the forest for the trees. Sure, we can find flaws in the current generation of LLMs. But they'll be fixed. We have a tool that can learn to do anything as well as a human, given sufficient input.
"trust us, it will work soon .. we just need a bit more time and a couple more dozens billions of dollars .. just trust us, bro .."
After re-reading the post once again, because I honestly thought I was missing something obvious that would make the whole thing make sense, I started to wonder if the author actually understands the scope of a computer language. When he says: > LLMs are far more nondeterministic than previous higher level languages. They also can help you figure out things at the high level (descriptions) in a way that no previous l…
Whether this is doable through orchestration or through carefully guided HITL by various specialists in their fields - or maybe not at all! - I suspect will depend on which domain you're operating in.
The intermediate product argument is the strongest point in this thread. When we went from assembly to C, the debugging experience changed fundamentally. When we went from C to Java, how we thought about memory changed. With LLMs, I'm still debugging the same TypeScript and Python I was before. The generation step changed. The maintenance step didn't. And most codebases spend 90% of their life in maintenance mode. Th…
I mean, we only have them because it is strictly necessary. If we could make architectures friendly to programming directly, we would have.
In that sense, high level languages are not a marvelous thing but a burden we have to carry because of the strict requirements of low level ones. The less burdens like those we have, the better.