Live data from Hacker News

AutoDev: Automated AI-driven development by Microsoft

arxiv.org

21–30 of 232 posts

Re: AutoDev: Automated AI-driven development by Microsoft

#21
post #10
post #2

If LLM/Agents contribute to software development, how does the role of software engineers evolve? SE should focus on : - System design - Integrations - Project management etc or the job will disappear in 10 years ?

Mainly get good at describing what you want. I think tests are good way of doing that, or some special requirements language will emerge that AI agents can use. I don't think English is particularly good way of describing things exactly. It often has ambiguous meanings which is where the bugs will come from.

How is code not just exactly that special requirements language you are looking for?

Re: AutoDev: Automated AI-driven development by Microsoft

#22
post #12
post #7

Great achievement, but what a horrible future we are facing. Instead of progressing towards more powerful programming interfaces with less cause for misinterpretation, we are going to automate the silly process of writing redundant unit tests to check if the behavior that we wanted was encoded properly. Why not skip this nonsense and have the code generated from the behavior in the first place?

Technically, the future does not have to be so gloomy. Soon the IA may built for itself the better tools we failed to build (or adopt). One can expect centralised intelligence to surpass collective intelligence, after all.

I would say it's debatable whether centralised intelligence can outperform collective intelligence. Centralised intelligence can be very efficient, but by definition it will lack the perspectives that a diverse collective intelligence can offer. In the long run, if the search for global optima is the ultimate goal, a diverse collective intelligence will have a higher chance of success than a centralised intelligence, especially in multidimensional spaces.

Re: AutoDev: Automated AI-driven development by Microsoft

#23

I can see this being used for code much like ChatGPT is used for prose - to generate large amounts of meaningless output of low quality and dubious utility, serving to fulfill pointless metrics at best, and enabling bad actors at worst. As with prose, good human crafted content will always be highly valued and rewarded.

Counterexample for the sake of argument: photography almost entirely replaced human painting.

Re: AutoDev: Automated AI-driven development by Microsoft

#24
post #15
post #11

Earlier quoted context omitted.

Yeah. The shocking speed of progress on AI - especially for coding - tells me quite clearly what the future holds for much of software engineering. Despite the human factors (yes, requirements gathering and specification is messy) our profession is intrinsically automatable at the end of the day. Being in denial is pointless.

I think software engineering will just go up the stack to requirements engineering. Those requirements will be specified as tests or in a very high level language that doesn't allow for ambiguous meanings. Which is essentially another programming language just more high level.

I basically agree. We'll have AI create some very high-level programming languages that suit various ways of specifying problems precisely, then program in those. Of course, the AI will also know how program in these languages, which will make development very accessible as you could describe a problem vaguely in natural language, get a specific solution back, then confirm it works for your needs or tweak it until it's suitable.

Re: AutoDev: Automated AI-driven development by Microsoft

#25
post #9

[flagged]

I'm not on the hype train myself, but I'd never say never. I can certainly picture much of what devs do today become automated. Heck, we already have plain old deterministic tools that are ridiculously productive compared to common tech stacks in the industry.

That said, it is the very nature of software development (or any endeavor in building complex systems) that we discover a lot of the detail problems later down the line. I don't think of concerns about something like this as "shifting goal posts", I think of them as refining our understanding of the nature of the problems (in this case, the nature of a developer's work).

Re: AutoDev: Automated AI-driven development by Microsoft

#27
post #2

If LLM/Agents contribute to software development, how does the role of software engineers evolve? SE should focus on : - System design - Integrations - Project management etc or the job will disappear in 10 years ?

Someone will still need to review the reams and reams of bullshit code generated by these Markov chains. It'll be like all your code gets written by first-term co-op students who have discovered alcohol for the first time and think it's pretty neat, but you're still responsible for the final output and don't get to do any of the fun and interesting stuff. Just constant, mind-numbing code reviews of something that might look OK on the surface but is really just blow-up punching clowns all the way down and already shipped by the marketing department because your backlog is massive and after all, you've been replaced by a random number generator fed through an incomplete Bayesian database of random bad code that costs so much less,

Re: AutoDev: Automated AI-driven development by Microsoft

#28
post #10

Earlier quoted context omitted.

Mainly get good at describing what you want. I think tests are good way of doing that, or some special requirements language will emerge that AI agents can use. I don't think English is particularly good way of describing things exactly. It often has ambiguous meanings which is where the bugs will come from.

How is code not just exactly that special requirements language you are looking for?

It's more about defining outcomes exactly rather than a sequence of exact steps.

Re: AutoDev: Automated AI-driven development by Microsoft

#29
post #8
post #7

Great achievement, but what a horrible future we are facing. Instead of progressing towards more powerful programming interfaces with less cause for misinterpretation, we are going to automate the silly process of writing redundant unit tests to check if the behavior that we wanted was encoded properly. Why not skip this nonsense and have the code generated from the behavior in the first place?

Because test define the behaviour. The hardest part of requirements is describing exactly what you want. Tests are great way of doing that. I think AI software development is going to involve writing tests, which the AI agents then get passing. Or some other requirements language that allows for exactness where English can fall down.

So we get to do the shitty part.
Post reply on HN