Man... I spent the last 6 months writing code using voice chat with multiple concurrent Claude code agents using an orchestration system because I felt like that was the new required skill set.
In the past few weeks I've started opening neovim again and just writing code. It's still 50/50 with a Claude code instance, but fuck I don't feel a big productivity difference.
I just write my own code and then ask AI to find any issues and correct them if I feel it is good advice. What AI is amazing at is writing most of my test cases. Saves me a lot of time.
To be fair, many human tests I've read do similar.
Especially when folks are trying to push % based test metrics and have types ( and thus they tests assert types where the types can't really be wrong ).
I use AI to write tests. Many of them the e2e fell into the pointless niche, but I was able to scope my API tests well enough to get very high hit rate.
The value of said API tests aren't unlimited. If I had to hand roll them, I'm not sure I would have written as many, but they test a multitude of 400, 401, 402, 403, and 404s, and the tests themselves have absolutely caught issues such as validator not mounting correctly, or the wrong error status code due to check ordering.
It's good at writing/updating tedious test cases and fixtures when you're directing it more closely. But yes, it's not as great at coming up with what to test in the first place.
Majority of data in typical message-passing plumbing code are a combination of opaque IDs, nominal strings, few enums, and floats. It's mostly OK for these cases, I have found. Esp. in typed languages.
Right. If AI actually made you more productive, there would be more good software around, and we wouldn't have the METR study showing it makes you 20% slower.
AI delivers the feeling of productivity and the ability to make endless PoCs. For some tasks it's actually good, of course, but writing high quality software by itself isn't one.
Ah, yes. LLM-assisted development. That thing that is not at all changing, that thing that different people aren’t doing differently, and that thing that some people aren’t definitely way better at than others.
I swear that some supposedly “smart” people on this website throw their ability to think critically out the window when they want to weigh in on the AI culture war.
B-but the study!
I can way with certainty that:
1. LLM-assisted development has gotten significantly, materially better in the past 12 months.
2. I would be incredibly skeptical of any study that’s been designed, executed, analysed, written about, published, snd talked about here, within that period of time.
This is the equivalent of a news headline stating with “science says…”.
Nobody is interested in your piece of anecdata and asserting that something has gotten better without doing any studies on it, is the exact opposite of critical thinking.
You are displaying the exact same thing that you were complaining about.
Really? The past two weeks I've been writing code with AI and feel a massive productivity difference, I ended up with 22k loc, which is probably around as many I'd have manually written for the featureset at hand, except it would have taken me months.
My work involves fixing/adding stuff in legacy systems. Most of the solutions AI comes up with are horrible. I've reverted back to putting problems on my whiteboard and just letting it percolate. I still let AI write most of the code once I know what I want. But I've stopped delegating any decision making to it.
Well at least for what I do, success depends on having lots of unit tests to lean on, regardless of whether it is new or existing code. AI plus a hallucination-free feedback loop has been a huge productivity boost for me, personally. Plus it’s an incentive to make lots of good tests (which AI is also good at)
Broadly speaking, maintaining a big std lib is a huge amount of work, so it makes sense that a language team is conservative about adding new surface to a stb lib which they will then have to maintain for a long time.
The work involved in maintaining a standard library is things like bug fixes. A larger standard library (or multi versions) means there's more likely to be bugs. You also have performance improvements, and when new versions of the language come out which has features to improve performance, you will most likely want to go back through and refactor some code to take advantage of it. You will also want to go through and refactor to make code easier to maintain. All of this just gets harder with a larger surface.
And the more stuff you pack into the standard library the more expertise you need on the maintenance team for all these new libraries. And you don't want a standard library that is bad, because then people won't use it. And then you're stuck with the maintenance burden of code that no one uses. It's a big commitment to add something to a standard library.
Every library is a liability especially in terms of api. There are many example where the first take on a problem within a std lib was a bad choice and required a major overhaul. Once something is in standard library it’s literally impossible to take it back without breaking the world if you don’t control api consumers
Yes, in python they break something at every release now. It's terrible. It mostly is because they remove modules from their standard library for no good reasons.
For example they've removed asyncore, their original loop-based module before the async/await syntax existed. All the software from that era needs a total rewrite. Luckily in debian for now the module is provided as a .deb package so I didn't have to do the total rewrite.
edit: as usual on ycombinator, dowvotes for saying something factually true that can be easily verified :D
The thread is about the code in the std lib being a huge amount of work because the code in the std lib needs to be kept working with new language releases.
And then you answered about downstream code breakage totally outside the std lib.
What would that entail, just a package whitelist? A few renamed packages? In the python 3 transition they renamed urllib2 to just urllib, but now it's almost a dead battery too and you want to use requests.
Honestly the problem was they did not go far enough. They hoped to have a minimal churn switch to avoid getting locked into bikeshedding for the rest of time. However, there was so little user user facing improvements that the required change hardly seemed worth porting. They also failed to initially offer any automatic porting tooling which could have increased adoption.
I will be forever mad that they did not use that as a breaking opportunity to namespace the standard library. Something like: `import std.io` so that other libraries can never conflict.
The problem is not that it is a draft RFC, the problem is that the library is unmaintained with an unresponsive developer who is squatting the uuid7 package name. It’s the top hit for Python developers who want to use UUIDv7 for Python 3.13 and below.
Your point is completely invalidated by useless name calling. The people behind cargo are clearly accomplished and serious individuals, and even if you disagree with some of the choices, calling them bozos makes your whole argument unconvincing.
I doesn't matter how it "should" work. In the real world you need to interact with external systems which don't have granular enough permission schemes.
People out here letting Claude code run CLIs using their own user permissions are morons waiting to have their data deleted.
CLI enables the actions to be made on behalf of you, the external service is not aware whether it's you or AI making the calls. With MCP, Sentry knows it's AI making the call so can be smarter about the security. There is many MCP annotation hints on tools to mark the as destructive, read-only etc.
That's interesting, but that still sounds like something a proper auth/token permission system would more than address. You're also actively choosing to limit what functionality MCP provides, which is fine, but there are many ways to do the same via the API or CLI tooling.
I'm not saying you are wrong to do this, I just don't think it's enough to convince me that yes this is the one true approach you should use.
That is presumably a very expensive endeavor. We already have hardware that attempts to mitigate this and while I think it's possible for the government it's certainly not trivial.
reply