Hacker Newsnew | past | comments | ask | show | jobs | submit | mohsen1's commentslogin

I am thinking about this a lot right now. Pretty existential stuff.

I think builders are gonna be fine. The type of programmer were people would put up with just because they could really go in their cave for a few days and come out with a bug fix that nobody else on the team could figure out is going to have a hard time.

Interestingly AI coding is really good at that sort of thing and less good at fully grasping user requirements or big picture systems. Basically things that we had to sit in meetings a lot for.


This has been my experience too. That insane race condition inside the language runtime that is completely inscrutable? Claude one-shots it. Ask it to work on that same logic to add features and it will happily introduce race conditions that are obvious to an engineer but a local test will never uncover.

> The type of programmer were people would put up with just because they could really go in their cave for a few days and come out with a bug fix that nobody else on the team could figure out is going to have a hard time.

Amen. It was a good time while it lasted.


All software engineers become pretty much the same in this world though. Anyone can sit in the meetings.

meetings hardly reach anywhere. most of the details are eventually figured out by developers when interacting with the code. If all ideas from PMs are implemented in a software, it would eventually turn into bloatware before even reaching MVP stage.

Not really, in my experience you still have to be good at solving problems to use it effectively. Claude (and other AI) can help folks find a "fix", but a lot of times it's a band-aid if the user doesn't understand how to debug / solve things themselves.

So the type of programmers you're talking about, who could solve complex problems, are actually just enhanced by it.


At this point, if you're paying out of pocket you should use Kimi or GLM for it to make sense

GLM is OK (haven't used it heavily but seems alright so far), a bit slow with ZAI's coding plan, amazingly fast on Cerebras but their coding plan is sold out.

Haven't tried Kimi, hear good things.


These are super slow to run locally, though, unless you've got some great hardware - right?

At least, my M1 Pro seems to struggle and take forever using them via Ollama.



It's not like he was the only one who came up with this idea. I built something like that without knowing about GasTown or Beeds. It's just an obvious next step

https://github.com/mohsen1/claude-code-orchestrator


I also share your confusion about him somehow managing to dominate credit in this space, when it doesn't even seem like Gastown ended up being very effective as a tool relative to its insane token usage. Everyone who's used an agentic tool for longer than a day will have had the natural desire for them to communicate and coordinate across context windows effectively. I'm guessing he just wrote the punchiest article about it and left an impression on people who had hitherto been ignoring the space entirely.

It was a fun article!

Exactly! I built something similar. These are such low hanging fruit ideas that no one company/person should be credited for coming up with them.

Seriously, I thought that was what langchain was for back in 2023.

Seriously, what is langchain? It’s so completely useless. Clearly none of the new agents care about it or need it. Irrelevant.

Agree, langchain was useless then and completely irrelevant now, but the idea that we need to orchestrate different LLM loops is extremely obvious.

> what is langchain?

and incantation you put on your resume to double your salary for a few months before the company you jumped ship to gets obsoleted by the foundational model


> Qodo takes a different approach by starting with real, merged PRs

Merged PRs being considered good code?


What do you suggest they use for ground truth?

I thought about this quite a bit. There are some nuggets in the open source code:

- vX.X.1 releases. when software was considered perfect but author had to write a fast follow up fix. very real bugs with real fixes

- Reverts. I'm sure anyone doing AI code review pays attention to this already. This is a sign of bad changes, but as important.

- PRs that delete a lot of code. A good change is often deleting code and making things simpler


For the first, your signal would be weak, for those events are rare. I don't think deleting and reverting is a signal of quality. Rather, it demonstrates bad changes, as you said. This does not tell the model what good code is, just what it is not.

I agree! It's a lot more pleasant than being stuck over figuring out how to use awk properly for hours. I knew what I needed to do then, and I know what I need to do now too. The difference is I get to results faster. Sometimes I even learn that awk was not even the right tool in my situation and learn about a new way of doing things while AI is "thinking" for me

I built an entire iOS app without opening Xcode UI even once. Why so many iOS engineers prefer XCode?

Is this bait? XCode has been a mainstay of iOS development ever since iOS was introduced and is a successor to Interface Builder on the Mac.

Why wouldn’t engineers prefer tools they’ve been using (mostly happily) for a decade+?


>Is this bait?

I don't think it's a serious question or the person is very young.

To answer the question. Xcode is the default IDE for iOS development. The default option will always be a practical choice.

JetBrains or Anthropic could get bought by a larger company or dismantled by the government somehow. Should anything happen to Apple (unlikely as that may seem) the entire iOS ecosystem would be gone as well negating any need for a default.


I wish I was young! I have used Xcode in the past. It's just way too slow and anything it does, other IDEs do faster for me.

Some influential iOS devs such as @dimillian and @steipete have moved away from Xcode or even xcodebuild where possible.

Which is completely fine. However these are people with lots of experience in Xcode already. People can have preferences including default options.

how did you debug it? The CLI tools are close to useless. I never even found a way to get console output from a device without Xcode.

What do you use instead? I thought Xcode sign-in is necessary for signing apps?

You can do the signing in Xcode Cloud. I'm sure with CLI it's possible too

There are command line tools which arguably are part of xcode, but you can drive them from the cli/ssh and don't need to interact with the xcode GUI.

> You’d have thought that GenAI would replace engineers

Trust me, it has replaced software engineers in many places. I don't hear anyone hiring junior software engineers around me


That’s because we’re in a recession. It has nothing to do with AI. AI can’t replace a god damn drive thru worker. McDonald’s literally tried and failed, that’s the funny part.

Weird. Most of the MacDonald's where I live use AI. And they're not the only ones. Doesn't seem like they failed.

MacDonald's is always trying "new" things intermittently in different markets. Removal from one market doesn't equal failure or permanence.

Most of the failures are a direct result of people intentionally trying to make it fail. Ordering a gazillion big macs and then replacing a third of them with egg mcmuffins is hardly something people would normally wish to do. Discoveries, like its inability to work with fractional food orders, are total nonsense since literally nobody orders food that way, unless they're trying to get lulz for their social accounts.


Oh hey, I've been running Werewolves/Mafia games as benchmarks for a while now

https://mafia-arena.com

Gemini is consistently winning against top models


not a problem for "AI". it's just a bit more spice (temperature) which Grok possibly need! jk!

I am trying! https://mafia-arena.com

I just don't have enough funding to do a ton of tests


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: