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

Claude Code: An Agentic cleanroom analysis

southbridge-research.notion.site

Post reply on HN
Print view View original

41–50 of 58 posts

Re: Claude Code: An Agentic cleanroom analysis

#41

Post by sebnado »

numeri wrote: post #23
InGoldAndGreen wrote: post #6

The "LLMs perspective" section is hiding at the end of this notion is a literal goldmine

No, it's completely useless, and puts the entire rest of the analysis in a bad light. LLMs have next to no understanding of their own internal processes. There's a significant amount of research that demonstrates this. All explanations of an internal thought process in an LLM are completely reverse engineered to fit the final answer (interestingly, humans are also prone to this – seen especially in split brain experi…

By saying that's its gold mine, I think OP meant that's it's funny, not that it brings valuable insight. ie: THEY KNOW -> that made me laugh

and as the article said "an LLM who just spent thousands of words explaining why they're not allowed to use thousands of words", its just funny to read.

Re: Claude Code: An Agentic cleanroom analysis

#42

Post by john2x »

elliotec wrote: post #36
scuff3d wrote: post #30

Earlier quoted context omitted.

If this is what software engineering is going to become I'm finding a new job.

Better start now! It’s incredible and unbelievable how productive it is. In my opinion it still takes someone with a staff level of engineering experience to guide it through the hard stuff, but it does in a day with just me what multiple product teams would take months to do, and better. I’m building a non-trivial platform as a solo project/business and have been working on it since about January. I’ve gotten more d…

Will these kinds of software end up like a programs written with bespoke Lisp macros? Lots of power but only one person actually knows it by heart.

Re: Claude Code: An Agentic cleanroom analysis

#45

Post by petetnt »

elliotec wrote: post #36
scuff3d wrote: post #30

Earlier quoted context omitted.

If this is what software engineering is going to become I'm finding a new job.

Better start now! It’s incredible and unbelievable how productive it is. In my opinion it still takes someone with a staff level of engineering experience to guide it through the hard stuff, but it does in a day with just me what multiple product teams would take months to do, and better. I’m building a non-trivial platform as a solo project/business and have been working on it since about January. I’ve gotten more d…

Designers and frontend developers don’t struggle with those. That’s why they are designers and frontend developers.

Before those 3 months you mentioned, how much did you spend time coding on average (at work, or as a hobby) percentagewise?

Re: Claude Code: An Agentic cleanroom analysis

#46

Post by ramoz »

ramoz wrote: post #40

For large codebases and task management, you can empower Claude Code with a simple filesystem framework. https://x.com/backnotprop/status/1929020702453100794 It sees everything it needs to in one pass, no extra reasoning or instruction tokens around things like MCP that abstract and create hops to simple understanding of where things are at.

There is something here about the native filesystem and tooling. & some type of insight into what agentic software engineering will look like - I mostly feel like an orchestrator, or validator in the terminal window next to Claude Code where i run tests/related things.

I was never a great terminal developer, I cant even type right - but Claude Code by far provides the best software engineering interface in there terms of LLM/agent UX.

Re: Claude Code: An Agentic cleanroom analysis

#47

Post by thegeomaster »

maleldil wrote: post #38
__mharrison__ wrote: post #14

Earlier quoted context omitted.

What does it give you that enabling Sonnet as a backend for Aider doesn't?

Claude Code is "agentic". Aider isn't. It can plan, use external tools, run the compiler, tests, linters, etc. You can do some of it with Aider, too, but Claude is more independent. The downside is that it can get very expensive, very fast.

I've personally found that I reject around 80% of suggestions with "No, and tell Claude what to do differently". So it requires a lot of babysitting, and it usually means I cannot do another thing effectively while it's running. For this reason I've considered switching to something less agentic like Aider since it's more predictable. Curious to hear how others work around this.

Re: Claude Code: An Agentic cleanroom analysis

#48

Post by SatvikBeri »

__mharrison__ wrote: post #14
triyambakam wrote: post #3

Claude Code with Sonnet 4 is so good I've stopped using Aider. This has been hugely productive. I've been able to write agents that Claude Code can spawn and call out to for other models, even.

What does it give you that enabling Sonnet as a backend for Aider doesn't?

It's much better at breaking down tasks on its own. All the tool use stuff is also deeply integrated. So I can reliably make a plan with Claude Code, then have it keep working on implementing until all tests pass.

Re: Claude Code: An Agentic cleanroom analysis

#49

Post by SatvikBeri »

thegeomaster wrote: post #47
maleldil wrote: post #38

Earlier quoted context omitted.

Claude Code is "agentic". Aider isn't. It can plan, use external tools, run the compiler, tests, linters, etc. You can do some of it with Aider, too, but Claude is more independent. The downside is that it can get very expensive, very fast.

I've personally found that I reject around 80% of suggestions with "No, and tell Claude what to do differently". So it requires a lot of babysitting, and it usually means I cannot do another thing effectively while it's running. For this reason I've considered switching to something less agentic like Aider since it's more predictable. Curious to hear how others work around this.

I found a huge difference between Sonnet 3.7 and Sonnet 4.0 here. Two weeks ago I rejected most suggestions, now I accept most of them.

In addition, after a 3 hour session I told it to create a CLAUDE.md that would help it program similarly to me, based on my preferences. I then edited that file a bit, and that has helped a lot.

Re: Claude Code: An Agentic cleanroom analysis

#50

Post by elliotec »

petetnt wrote: post #45
elliotec wrote: post #36

Earlier quoted context omitted.

Better start now! It’s incredible and unbelievable how productive it is. In my opinion it still takes someone with a staff level of engineering experience to guide it through the hard stuff, but it does in a day with just me what multiple product teams would take months to do, and better. I’m building a non-trivial platform as a solo project/business and have been working on it since about January. I’ve gotten more d…

Designers and frontend developers don’t struggle with those. That’s why they are designers and frontend developers. Before those 3 months you mentioned, how much did you spend time coding on average (at work, or as a hobby) percentagewise?

Of course they do. I’ve been primarily a front end developer for 15 years. Working with designers. Shit takes so many iterations and so much time. Claude is faster but still “struggles” compared to basic rails work and API calls and test writing and whatnot.

I’m not sure how to answer the question on percentage of time coding. I quit my job as a director where coding wasn’t part of the job but have kept up on side stuff and architecture at work. Since the new year when I started this it’s been in bursts, some weeks or nights I’ll go super hard coding and others I’ll focus on other stuff. I go to conferences and study a lot on the subject of the industry so that’s what I do in bursts of the non-coding time.

I hired a virtual assistant to help with the non-coding things so lately it’s been a lot more.

In general I’d estimate at least 50% of my work on this thing since January has been coding but it’s really hard to gauge. Claude over the past 3 days has surpassed my personal coding productivity over the past 3 months though, if it wasn’t clear what I was saying.

Post reply on HN