291–300 of 580 posts
Earlier quoted context omitted.
The plan is to improve AI agents from their current ~intern level to a level of a good engineer.
Yes but they are supposed to be PhD level 5 years ago if you are listening to sama et al.
Earlier quoted context omitted.
I feel like everyone is applying a worse-case narrative to what's going on here.. I see this as a work in progress.. I am almost certain the humans in the loop on these PRs are well aware of what's going on and have their expectations in check, and this isn't just "business as usual" like any other PR or work assignment. This is a test. You can't improve a system without testing it on real world conditions. How do we…
You are not addressing the point in the comment, why are failing CI changes assigned?
So the typical expectations or norms of how code reviews and PRs work between humans don't really apply here.
That's my guess at least. I have no more insider information than you.
Well, the coding agent is pretty much a junior dev at the moment. The seniors are teaching it. Give it a 100k PRs with senior developer feedback and it'll improve just like you'd anticipate a junior would. There is no way that FANG aren't using the comments by the seniors as training data for their next version. It's a long-term play to have pricey senior developers argue with an llm
Earlier quoted context omitted.
> At least opening PRs is a safe option, you can just dump the whole thing if it doesn't turn out to be useful. There's however a border zone which is "worse than failure": when it looks good enough that the PRs can be accepted, but contain subtle issues which will bite you later.
Yep. I've been on teams that have good code review culture and carefully review things so they'd be able to catch subtle issues. But I've also been on teams where reviews are basically "tests pass, approved" with no other examination. Those teams are 100% going to let garbage changes in.
Earlier quoted context omitted.
It’s not 20, it’s 200+. And that will only get more expensive.
Again I don't know what people mean when they say it will get more expensive. This is a wrong way of looking at the issue. Pretty sure cars are more expensive than horse carriage, or that iPhones are/were more expensive than button phones. You can cite so many such examples. Like photocopying machines, or cameras, or wrist watches, or even things like radio, television etc. More importantly, sometimes how you do thin…
LLMs are being made into another rental extraction system and should be viewed as such.
As an outside observer but developer using .NET, how concerned should I be about AI slop agents being let lose on codebases like this? How much code are we going to be unknowingly running in future .NET versions that was written by AI rather than real people?
What are the implications of this around security, licensing, code quality, overall cohesiveness, public APIs, performance? How much of the AI was trained on 15+ year old Stack Overflow answers that no longer represent current patterns or recommended approaches?
Will the constant stream of broken PR's wear down the patience of the .NET maintainers?
Did anyone actually want this, or was it a corporate mandate to appease shareholders riding the AI hype cycle?
Furthermore, two weeks ago someone arbitrarily added a section to the .NET docs to promote using AI simply to rename properties in JSON. That new section of the docs serves no purpose.
How much engineering time and mental energy is being allocated to clean up after AI?
Earlier quoted context omitted.
I feel like everyone is applying a worse-case narrative to what's going on here.. I see this as a work in progress.. I am almost certain the humans in the loop on these PRs are well aware of what's going on and have their expectations in check, and this isn't just "business as usual" like any other PR or work assignment. This is a test. You can't improve a system without testing it on real world conditions. How do we…
I was looking for exactly this comment. Everybody's gloating, "Wow look how dumb AI is! Haha, schadenfreude!" but this seems like just a natural part of the evolution process to me. It's going to look stupid... until the point it doesn't. And my money's on, "This will eventually be a solved problem."
I have met people who believe that automobile engineering peaked in the 1960's, and they will argue that until you are blue in the face.
Earlier quoted context omitted.
I know this is meant to sound witty or clever, but who actually wants to behave this way at their job? I'll never understand the antagonistic "us vs. them" mentality people have with their employer's leadership, or people who think that you should be actively sabotaging things or be "maliciously compliant" when things aren't perfect or you don't agree with some decision that was made. To each their own I guess, but I…
It’s worth recognizing that the tension between labor and capital historical reality, not just a modern-day bad attitude. Workers and leadership don’t automatically share goals, especially when senior management incentives often prioritize reducing labor costs which they always do now (and no, this wasn't always universally so). Most employees want to do good work, but pretending there’s no structural divergence in i…
But 100% agreed that everyone should maintain a realistic expectation and understanding of their relationship with their employer, and that job security and employment guarantees are possibly at an all-time low in our industry.
Earlier quoted context omitted.
Depends on team but seems management is pushing it from https://news.ycombinator.com/item?id=44031432 "From talking to colleagues at Microsoft it's a very management-driven push, not developer-driven. Friend on an Azure team had a team member who was nearly put on a PIP because they refused to install the internal AI coding assistant. Every manager has "number of developers using AI" as an OKR, but anecdotally most d…
> management is pushing it Why?