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

41–50 of 65 posts

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

#41

Post by aitchnyu »

louiereederson wrote: post #24
golly_ned wrote: post #5

I came away with a very different conclusion, which is that the fact that such “bad” software can be so resoundingly successful for a business, yet be so odious to experienced human reviewers, means that it was the right engineering choice to go fast, rather than “do things right” by emphasizing code quality. What good would it truly be if a 3K line function is split into 8 modules? It’ll be neater and more comprehen…

Successful over what time frame? It's way too early to declare victory.

Is there some testable/observable prediction where Opencode beats CC and Nanoclaw beats Openclaw?

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

#42

Post by ninininino »

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?

They don't work. Do not trust them. Run Claude Code in an isolated, disposable micro VM and assume it will break your environment, steal any available secrets, do destructive commands, etc. So don't give it any way to do that to anything you care about.

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

#43

Post by jgalt212 »

> Issue #38335 had 201 upvotes and zero team responses. Labeled “invalid.”

They're doing the right thing. The market is resoundingly telling them this.

> Anthropic draws VC interest at up to $800 billion valuation, Business Insider reports

https://www.reuters.com/legal/transactional/anthropic-draws-...

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

#44

Post by jmux »

nurettin wrote: post #36
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.

if you read the thinking context while in plan mode (I had it shown to me, i think mistakenly, by switching modes while Claude was thinking a week or so ago) plan mode is just a pre-prompt saying “you are now in plan mode, don’t propose edits, read the code and understand how it works.”

it’s not an actual limitation on the harness.

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

#45

Post by therobots927 »

golly_ned wrote: post #5

I came away with a very different conclusion, which is that the fact that such “bad” software can be so resoundingly successful for a business, yet be so odious to experienced human reviewers, means that it was the right engineering choice to go fast, rather than “do things right” by emphasizing code quality. What good would it truly be if a 3K line function is split into 8 modules? It’ll be neater and more comprehen…

Wow this industry is so cooked. Good God almighty.

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

#46

Post by adampunk »

redhale wrote: post #19
golly_ned wrote: post #5

I came away with a very different conclusion, which is that the fact that such “bad” software can be so resoundingly successful for a business, yet be so odious to experienced human reviewers, means that it was the right engineering choice to go fast, rather than “do things right” by emphasizing code quality. What good would it truly be if a 3K line function is split into 8 modules? It’ll be neater and more comprehen…

But it is working primarily because of the Max subscription model. If I could use my Max subscription to get $5000 worth of tokens for only $200 via OpenCode or Pi, I would drop Claude Code today. I think a lot of people (and enterprises) are of a similar opinion. Not saying Claude Code would have no users, but its dominance would be greatly diminished.

But you can’t and the reason that you care also has to do with the same production process.

It’s not like a separate company made the terminal app versus the model. If we think that the desktop app is bad, but the model is good then that’s still an endorsement of the software process.

If we think the model doesn’t matter at all, then that’s an even bigger endorsement. Is the model has no content worth talking about over the nearest competitors or an open source alternative, then the remainder is marketing and polish.

I just don’t understand how people can look at a company that is capacity constrained in this market and think that they’re doing things poorly.

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

#47

Post by adampunk »

lsaferite wrote: post #33
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.

Every time I hear someone say that software is successful in spite of something I find that looking harder shows some interesting choices.

If this software succeeds despite the manifest failures that are pointed out here, that’s a sign that something is working. We could argue that something is just access to the model, but plenty of other companies sell that and they don’t seem to do as well.

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

#48

Post by beacon294 »

Alifatisk wrote: post #40
beacon294 wrote: post #13

Earlier quoted context omitted.

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

It was my intent but it's also fine to be more direct.

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

#49

Post by allan_s »

redhale wrote: post #19
golly_ned wrote: post #5

I came away with a very different conclusion, which is that the fact that such “bad” software can be so resoundingly successful for a business, yet be so odious to experienced human reviewers, means that it was the right engineering choice to go fast, rather than “do things right” by emphasizing code quality. What good would it truly be if a 3K line function is split into 8 modules? It’ll be neater and more comprehen…

But it is working primarily because of the Max subscription model. If I could use my Max subscription to get $5000 worth of tokens for only $200 via OpenCode or Pi, I would drop Claude Code today. I think a lot of people (and enterprises) are of a similar opinion. Not saying Claude Code would have no users, but its dominance would be greatly diminished.

Its the same for a lot of bundled things, mac hardware + os or windows pre-installed, chrome being pushed by google.com etc.

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

#50

Post by lsaferite »

adampunk wrote: post #47
lsaferite wrote: post #33

Earlier quoted context omitted.

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.

Every time I hear someone say that software is successful in spite of something I find that looking harder shows some interesting choices. If this software succeeds despite the manifest failures that are pointed out here, that’s a sign that something is working. We could argue that something is just access to the model, but plenty of other companies sell that and they don’t seem to do as well.

In this case it's because they gate subscription access to their agent. If not for that, I wouldn't be using Claude Code. I like Anthropic overall, but it disappoints me that they didn't make CC open source and that they insist on tying subscription use to CC.
Post reply on HN