Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

What Claude Code's Source Revealed About AI Engineering Culture

techtrenches.dev

Post reply on HN
Print view View original

31–40 of 65 posts

Re: What Claude Code's Source Revealed About AI Engineering Culture

#31

Post by K0balt »

otabdeveloper4 wrote: post #22
K0balt wrote: post #6

Obviously they were legit vibing it. AI coding is like having a team of 100 interns. It’s incredibly powerful but you need to keep it under control or you’re gonna have a bad day. Write documentation describing the specs , the APIs, the protocols, and the customer stories. Specify that everything must be divided with clear separations of concerns, interfaces, and state objects. Any single file should have a clearly d…

Sounds like a lot of work just to avoid doing work. Can I just type out the code instead? Please?

It is a lot of work, but I’m much more productive and produce better code than when I was running a small team. And I’m not spending 36k a month. As a research stage startup, that’s a really big deal.

I’ve been writing code for nearly 50 years now, and the only thing I like better than coding is getting things done. For me, AI is rocket fuel if you do it right, and a bunch of hypergolic liquid if you don’t.

Re: What Claude Code's Source Revealed About AI Engineering Culture

#32

Post by R00mi »

I agree with the core of what you're saying, but I think the real split isn't "Anthropic trustworthy or not" — it's: what's proprietary vs what's open in the stuff you're actually building on. Routines, Projects, Artifacts, Skills — that's vendor-specific, disposable by definition. MCP, CLAUDE.md, markdown in your repo — that's portable. If Anthropic pivots or nerfs the thing tomorrow, you just rewire your MCP tools onto another harness in 10 minutes. Personally I build my agent workflows as scripts + MCP tools — called by Claude Code today, callable by whatever harness replaces it tomorrow. The building block is "a set of MCP tools + one CLAUDE.md", not "a Routine defined in Anthropic's console". Functionally the same, zero lock-in. Routines are fine for quick-wins, but the moment you start stacking them into a real workflow you're just moving your tech debt into a proprietary format. At that point you might as well externalize to scripts from the start.

Re: What Claude Code's Source Revealed About AI Engineering Culture

#33

Post by lsaferite »

j_bum wrote: post #2

As someone who finds a huge amount of enjoyment in developing using Opus 4.6 in Claude code, I’d love to know what other harnesses people use that deliver the same experience as CC. CC is a vibe-coded mess, but it works very well for me. I do a lot of work in R and find codex (5.4 & 5.3-codex) just totally drop the ball with R. Anthropic’s models are far better with R, so I use them. But I do wonder how much the harn…

CC is riddled with bugs and poor UI/UX. It's effective in spite of that. Just think what a well-designed agent would do in place of that. I don't use other coding agents currently because the subscription with CC gets me what I need and I don't want to pay retail token rates. I would 100% prefer an open source agent so I could fork it and tweak it to my needs.

Re: What Claude Code's Source Revealed About AI Engineering Culture

#35

Post by all_factz »

adrian_b wrote: post #12
simianwords wrote: post #11

Earlier quoted context omitted.

Your kind of critique forgets the tradeoff between getting something out quick vs doing something slowly and nicely. If you choose slowly, you are depriving your users of the value from your app for a long time. It’s not as clear a choice as you think

Have you read my entire comment? I have already said that sometimes time-to-market is the most important, so that should be the priority, but the advantage of delivering immediately the application is only temporary, so you must improve quickly your first possibly vibe-coded implementation, otherwise better alternatives will be delivered by others. Claude Code is an obvious example of this, because it has practically…

They would have to trade off building new features for refactoring. It seems they consider shipping more important, and that as long as the existing features mostly work, that’s good enough. As customers, we have to ask: do we agree? Do we want features over stability? I think the answer is yes, at least for me (and the market seems to agree). But it’s certainly a risk Anthropic is taking.

I will note that this strategy only really makes sense because Anthropic controls the compute. If open-source harnesses could also use Claude max plans, then they’d have to focus much more on stability and quality, or just build an open-source harness themselves, or probably better yet, get out of the harness-building business altogether. So they’re gambling on staying ahead of open-source models, which seems like it’s been a good bet so far, but we’ll see.

Re: What Claude Code's Source Revealed About AI Engineering Culture

#36

Post by nurettin »

markisus wrote: post #34

Claude code has some basic security features like asking for user confirmation for bash commands, or restricting commands to the current directory. If these features are not being code reviewed, what assurances do we have that they actually work?

You don't. I learned this from it executing commands while in plan mode. It is LLMs all the way down.

Re: What Claude Code's Source Revealed About AI Engineering Culture

#37

Post by ryandrake »

haspok wrote: post #25

> I’m seriously considering a pivot to security Exactly my conclusion, unfortunately I'm too old to pivot now, but anyone in their junior-to-mid days as a software developer should consider this pivot. And this is only about generating source code in a closed environment. All hell will break loose when Openclaw et al get in the hands of average users...

I wouldn't. Until companies become liable for their security failures, and that liability comes with a big price tag, there will be no money in security. Currently, poor security costs companies nothing, so they won't pay to improve their security.

Re: What Claude Code's Source Revealed About AI Engineering Culture

#38

Post by nonameiguess »

simianwords wrote: post #14
adrian_b wrote: post #12

Earlier quoted context omitted.

Have you read my entire comment? I have already said that sometimes time-to-market is the most important, so that should be the priority, but the advantage of delivering immediately the application is only temporary, so you must improve quickly your first possibly vibe-coded implementation, otherwise better alternatives will be delivered by others. Claude Code is an obvious example of this, because it has practically…

The advantage is definitely not temporary as can be seen by how many people use codex vs Claude code. Claude code works just fine and I have zero issues at usability level. Could they have more features? Yes but I see that they are shipping quick. It is obvious to me that they took the right balance between time to market and clan code

These discussions are insane. No agentic coding product, including Claude Code, has existed for a full year yet, but people are stating with extreme confidence who has "won" the competition to be the leading or even only provider of this kind of product and having heated arguments over whether or not we can consider the current state of the market to be temporary or not. Imagine having this same argument about Lycos versus Yahoo! in 1995.

Re: What Claude Code's Source Revealed About AI Engineering Culture

#39

Post by Alifatisk »

_menelaus wrote: post #27
voidfunc wrote: post #4

Earlier quoted context omitted.

I used OpenCode and find it works just as well or better than CC. I dont think CC has a moat other than their model but their model is also available through Copilot.

Have you found any cheaper models to work well with OpenCode? Like any of the Chinese models?

I use Z.ai GLM-5.1 with Opencode, haven't had any issues.

Re: What Claude Code's Source Revealed About AI Engineering Culture

#40

Post by Alifatisk »

beacon294 wrote: post #13
j_bum wrote: post #2

As someone who finds a huge amount of enjoyment in developing using Opus 4.6 in Claude code, I’d love to know what other harnesses people use that deliver the same experience as CC. CC is a vibe-coded mess, but it works very well for me. I do a lot of work in R and find codex (5.4 & 5.3-codex) just totally drop the ball with R. Anthropic’s models are far better with R, so I use them. But I do wonder how much the harn…

Pi

No one is going to find out exactly what you mean. I'll add this link for reference, https://lucumr.pocoo.org/2026/1/31/pi
Post reply on HN