Earlier quoted context omitted.
Your statement is factually wrong, Claude 3.5v2 asks clarifying questions when needed "natively", and you can add similar instructions in your prompt for any model.
The default system prompts are tuned for the naive case. LLMs being all purpose text handling tools, can be reprogrammed for any behavior you wish. This is the crux of skilled use of LLMs. The better the LLMs get, the worse the average prompt quality.
Thoughts on a month with Devin
141–150 of 194 posts
Re: Thoughts on a month with Devin
#142Earlier quoted context omitted.
It's just vscode. I greatly prefer vim but the difference between vim + ai tools and cursor is just a no brainer in terms of productivity. Cursor isn't without problems but it's leagues ahead of the competition in my opinion.
I've been tempted to try Cursor because of vocal fans like yourself. Then I went to their website and forums yesterday. I am no longer tempted.
Re: Thoughts on a month with Devin
#143Earlier quoted context omitted.
My first job I spent so much time reading Python docs, and the ancient art of Stack Overflow spelunking. But I could intuitively explain a solution in seconds because of my CS background. I used to encounter a certain kind of programmer often, who did not understand algorithms well but had many years of experience with a language like Ruby, and thus was faster in completing tasks because they didn't need to do the re…
I disagree. If anything, CS degrees have proven time and time again they aren't translatable into software development (which is why there's an entire degree field called Software Engineering emerging). If anything, my gut says that the CS concepts are very easy for LLMs to recall and will be the first things replaced (if ever) by AI. Software engineer{ing,s} (project construction, integrations, scaling, organization…
In many places where someone might reach for something they remember from their CS coursework, there's often an open-source library or tool doing much the same thing. Understanding how these libraries and tools function is certainly valuable but, much of the time, people can get by with only a vague hunch; indeed, this is why they exist! IMHO, I would be happier with the LLM assistant if it picked reliable library code rather than writing up a sketchy solution of its own.
I'm also familiar with this idea people who have managed to be successful in the field without a CS degree are more capable. In my opinion, this is hogwash. I think if we take a step back, we'll see that people graduating from established, top-tier CS programs are looking for higher pay than those who have come from a less expensive and (very often) business focused program. To be fair, people from each of these backgrounds has their strengths; in many organizations a developer who has done two semesters of accounting is a real benefit, in others the ability to turn a research paper into the prototype of a new product is going to be important.
Years of experience often washes out much of these differences. People who have started from business oriented education programs may end up taking a handful of CS courses as they navigate their career, likewise many people with a CS background end up accruing business centered skills.
In my opinion, people start out their education at a place that they can afford, a place that is familiar to them, often a place that they feel comfortable. Someone's economic background (and of their family) plays a big role on what kind of educational program they choose when they are on the cusp of adulthood. Smart and talented people can always learn what they need to learn, regardless of their starting point.
Re: Thoughts on a month with Devin
#144Earlier quoted context omitted.
I completely agree with you. More precisely, I feel they are useful when you have specific tasks with limited scope. For instance, just yesterday I was battling with a complex SQL query and I got halfway there. I gave our bot the query and an half assed description of what I wanted/what was missing and it got it right on the first try.
Are you sure that your SQL query is correct?
Re: Thoughts on a month with Devin
#145As someone who uses AI coding tools daily and has done a fair amount of experimentation with different approaches (though not Devin), I feel like this tracks pretty well. The problem is that Devin and other "agentic" approaches take on more than they can handle. The best AI coders are positioned as tools for developers, rather than replacements for them. Github Copilot is "a better tab complete". Sure, it's a neat de…
When I tried Copilot the "better tab complete" felt quite annoying, in that the constantly changing suggested completion kept dragging my focus away from what I was writing. That clearly doesn't happen for you. Was that something you got used to over time, or did that just not happen for you? There were elements of it I found useful, but I just couldn't get over the flickering of my attention from what I was doing to…
> existing codebase in the form of a VSCode project / GitHub repo and uses that as a basis for suggestions
What are you actually looking for? Copilot uses "all of github" via training, and your current project in the context.
Re: Thoughts on a month with Devin
#146Earlier quoted context omitted.
I recommend you look at tools like Aider or Codebuff... sure they need to call some LLM at some point (could be your own, could be external), but the key thing that they are doing complex modifications of source code using things like treesitter -> i.e. you don't rely directly on the LLM modifying code, but the LLM using trees to modify the code. See in Aider's sourcecode: https://github.com/Aider-AI/aider/tree/main/…
Can Aider sit inside VS Code, understand what files I have open, and use them as context? Their docs lead me to say no, that they are an inline chat/completion experience
Re: Thoughts on a month with Devin
#147Earlier quoted context omitted.
When I tried Copilot the "better tab complete" felt quite annoying, in that the constantly changing suggested completion kept dragging my focus away from what I was writing. That clearly doesn't happen for you. Was that something you got used to over time, or did that just not happen for you? There were elements of it I found useful, but I just couldn't get over the flickering of my attention from what I was doing to…
I have the automatic suggestions turned off. I use a keybind to activate it when I want it. > existing codebase in the form of a VSCode project / GitHub repo and uses that as a basis for suggestions What are you actually looking for? Copilot uses "all of github" via training, and your current project in the context.
I didn't realise you could do that. Might give it another go.
> Copilot uses "all of github" via training, and your current project in the context.
The current project context is the bit I didn't think it had. Thanks!
Re: Thoughts on a month with Devin
#148Earlier quoted context omitted.
> The best AI coders are positioned as tools for developers, rather than replacements for them. I agree with this. However, we must not delude ourselves and understand that corporate is pushing for replacement . So there will be a big push to improve on tools like Devin. This is not a conspiracy theory, in many companies (my wife's, for example) they are openly stating this: we are going to reduce (aka "lay off") the…
I remember when I was first getting started in the industry the big fear of the time was that offshoring was going to take all of our jobs and drive down the salaries of those that remained. In fact the opposite happened: it was in the next 10 years that salaries ballooned and tech had a hiring bubble. Companies always want to reduce staff and bad companies always try to do so before the solution has really proven it…
Unlike with offshoring, this is a technological solution, which understandably is received more enthusiastically on HN. I get it. It's interesting as tech! And it's achieved remarkable things. But unlike with offshoring (which is a people thing) or magical NOCODE/CASE/etc "solutions", it seems the consensus is that AI coding assistants will eventually get there. At least a portion of even HN seems to think so. And some are cheering!
The coping mechanism seems to be "it won't happen to me" or "my knowledge is too specialized" but I think this will become increasingly false. And even if your knoweldge is too specialized to be replaced by AI, most engineers aren't like that. "Well, become more specialized" is unrealistic advice, and in any case, the employment pool will shrink.
PS: I am offhsoring (in a way). I'm not based in the US but I work remotely for a US company.
Re: Thoughts on a month with Devin
#149Earlier quoted context omitted.
> I wonder how many of us, here, understand that many jobs are going away if/when this works out for the companies. And the usual coping mechanism, "it will only be for low hanging fruit", "it will never happen to me because my $SKILL is not replaceable", will eventually not save you. Sure, if you are a unique expert on a unique field, but many of us don't have that luxury. And it'll be used to drive down salaries, t…
> Ok then why does nearly every company make people write code for interviews or do take home programming projects? For the same reason they put leetcode problems to "test" an applicants skill. Or have them write mergesort on a chalkboard by hand. It gives them a warm fuzzy feeling in the tummy because now they can say "we did something to check they are competent". Why, you ask? Well it's mostly impossible to come u…
When AI becomes able to do most non-programming tasks too, say design or solving open-ended problems (yeah, except in trivial cases it cannot -- for now) we can have this conversation again...
I think saying "well, programming is not important, what matters is $THING" is a coping mechanism. Eventually AI will do $THING acceptably enough for the bean counters to push for more layoffs.
Re: Thoughts on a month with Devin
#150I'm one of the creators of OpenHands (fka OpenDevin). I agree with most of what's been said here, wrt to software agents in general. We are not even close to the point where AI can "replace" a software engineer. Their code still needs to be reviewed and tested, at least as much as you'd scrutinize the code of a brand new engineer just out of boot camp. I've talked to companies who went all in on AI engineers, only to…