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

How Claude Code works in large codebases

claude.com

Post reply on HN
Print view View original

11–20 of 191 posts

Re: How Claude Code works in large codebases

#11

Post by weird-eye-issue »

wood_spirit wrote: post #9

I’m super interested to know what the back and forth between models and tools really looks like in practice. Are there any much more detailed walkthroughs of how it works and how it decides the tools to use and the grep to use etc and what the conversations actually look like? In the UI you see just enough to know it’s doing something but you don’t really see the jumps it’s making offscreen.

You can easily inspect the full requests it makes to the API which contains the full system prompt, tools, tool calls, etc.

Re: How Claude Code works in large codebases

#12

Post by SpicyLemonZest »

Tsarp wrote: post #4

Wondering if enterprises have a modified version of CC that doesnt have to optimize to stop bleeding on fixed cost subscription plans. The article really does not align with the current sentiment. Everyone with a choice has mostly moved on to codex (ofc in this world all it takes is a model update/harness update to turn things around). CC is great at a lot of things, but repeatedly misses out reading on crucial parts…

I think it's a good rule of thumb that if you find yourself saying everyone prefers this model or that model you're in a bubble. I've made this mistake before, I used to go around saying everyone knew Claude was the only model for serious professional use, but I was wrong.

Re: How Claude Code works in large codebases

#13

Post by Reebz »

Tsarp wrote: post #4

Wondering if enterprises have a modified version of CC that doesnt have to optimize to stop bleeding on fixed cost subscription plans. The article really does not align with the current sentiment. Everyone with a choice has mostly moved on to codex (ofc in this world all it takes is a model update/harness update to turn things around). CC is great at a lot of things, but repeatedly misses out reading on crucial parts…

The influencer economy trades on hype, on frenzy, and ultimately, eyeballs. The more the better.

They want you feel like you’re missing out. They want you to switch. Being boring is far more productive. Pin your versions. Stick to stable releases and avoid the nightlies.

Significant noise created from 4.6 to 4.7 Opus transition has caused some to interpret this as signal. Excluding certain genuine and real bugs, the noise about perceived quality falling dramatically was noise. Influencers doing influencing turned it into “signal”. The reality was that if you had strong planning and spec driven development it ranged from manageable to non-existent.

The vast majority of the people I know and work with have not switched off CC or their Max sub.

Re: How Claude Code works in large codebases

#14

Post by ghiculescu »

Tsarp wrote: post #4

Wondering if enterprises have a modified version of CC that doesnt have to optimize to stop bleeding on fixed cost subscription plans. The article really does not align with the current sentiment. Everyone with a choice has mostly moved on to codex (ofc in this world all it takes is a model update/harness update to turn things around). CC is great at a lot of things, but repeatedly misses out reading on crucial parts…

[dead]

Re: How Claude Code works in large codebases

#15

Post by sigmar »

SpicyLemonZest wrote: post #12
Tsarp wrote: post #4

Wondering if enterprises have a modified version of CC that doesnt have to optimize to stop bleeding on fixed cost subscription plans. The article really does not align with the current sentiment. Everyone with a choice has mostly moved on to codex (ofc in this world all it takes is a model update/harness update to turn things around). CC is great at a lot of things, but repeatedly misses out reading on crucial parts…

I think it's a good rule of thumb that if you find yourself saying everyone prefers this model or that model you're in a bubble. I've made this mistake before, I used to go around saying everyone knew Claude was the only model for serious professional use, but I was wrong.

I always assume that people making those comments on HN are trying to convince others to switch to their model. Surely no one actually believes their friend circle is a representative sample of the hundreds of millions of people that use these LLMs?

Re: How Claude Code works in large codebases

#16

Post by zarzavat »

Tsarp wrote: post #10
Aeolun wrote: post #5

Earlier quoted context omitted.

You must be using a different CC. Or what they’re writing here is correct, and it’s all due to the CLAUDE.md file that I only occassionally yell at claude.

Hmm please share more. I have had the max CC sub since it came out. Religiously follow all of Boris/Cats advice but still struggle with it. Meanwhile a really badly written AGENTS.md will still get the work done.

Apologies but what is a Boris Cat?

Re: How Claude Code works in large codebases

#17

Post by sprobertson »

weird-eye-issue wrote: post #11
wood_spirit wrote: post #9

I’m super interested to know what the back and forth between models and tools really looks like in practice. Are there any much more detailed walkthroughs of how it works and how it decides the tools to use and the grep to use etc and what the conversations actually look like? In the UI you see just enough to know it’s doing something but you don’t really see the jumps it’s making offscreen.

You can easily inspect the full requests it makes to the API which contains the full system prompt, tools, tool calls, etc.

or easier, open ~/.claude/projects/[project]/[session].jsonl (excluding the system prompt)

Re: How Claude Code works in large codebases

#19

Post by paustint »

Tsarp wrote: post #4

Wondering if enterprises have a modified version of CC that doesnt have to optimize to stop bleeding on fixed cost subscription plans. The article really does not align with the current sentiment. Everyone with a choice has mostly moved on to codex (ofc in this world all it takes is a model update/harness update to turn things around). CC is great at a lot of things, but repeatedly misses out reading on crucial parts…

I have a choice and have not moved to codex (100/mo personal + my employer pays for a subscription). I try codex here and there and it seems to go off the rails every time. I have had some good experiences with codex, but generally trying to get something big accomplished it doesn't work out.

But I may not have paid enough to get the full real experience with codex

Post reply on HN