News for hackers. Stuff that matters.
Re:Claude Code: An Agentic cleanroom analysis by triyambakam on Sunday June 01, 2025 @05:55PM (#44154020)
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.
Re:Claude Code: An Agentic cleanroom analysis by __mharrison__ on Sunday June 01, 2025 @06:32PM (#44154241)
What does it give you that enabling Sonnet as a backend for Aider doesn't?
Re:Claude Code: An Agentic cleanroom analysis by maleldil on Sunday June 01, 2025 @07:29PM (#44154549)
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.
Re:Claude Code: An Agentic cleanroom analysis by thegeomaster on Sunday June 01, 2025 @07:44PM (#44154640)
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 by SatvikBeri on Sunday June 01, 2025 @08:27PM (#44154869)
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 by rane on Monday June 02, 2025 @04:14AM (#44156663)
Give better and more precise instructions.

Use the @ thing to prod it read some relevant files for context (kind of like with Aider)

Re:Claude Code: An Agentic cleanroom analysis by maleldil on Monday June 02, 2025 @12:03PM (#44160243)
My experience has been quite different. I often give it a large block of instructions and let it run autonomously for a while. When I come back it often did what I expected. It doesn't have good taste with respect to APIs, though, so sometimes I need a heavier hand on that.

I find it helps to have a CLAUDE.md file with instructions and thorough documentation. This is on a ~30k LOC Python codebase with type-checking and tests. YMMV with other languages.

Re:Claude Code: An Agentic cleanroom analysis by ramoz on Sunday June 01, 2025 @07:27PM (#44154537)
An entirely different software and agent architecture - built by the creators of Claude themselves.
Re:Claude Code: An Agentic cleanroom analysis by SatvikBeri on Sunday June 01, 2025 @08:26PM (#44154862)
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 by cedws on Sunday June 01, 2025 @06:33PM (#44154245)
Could you briefly explain your workflow? I use Zed’s agent mode and I don’t really understand how people are doing it purely through the CLI. How do you get a decent workflow where you can approve individual hunks? Aren’t you missing out on LSP help doing it in the CLI?
Re:Claude Code: An Agentic cleanroom analysis by mindwok on Sunday June 01, 2025 @06:56PM (#44154357)
Claude code has a VS Code plugin now that lets you view and approve diffs in the editor. Before it did that, I really don't understand how people got anything of substance done because it simply isn't reliable enough over large codebases.
Re:Claude Code: An Agentic cleanroom analysis by phillipcarter on Sunday June 01, 2025 @07:16PM (#44154484)
I managed this (and still do) just fine by using source control. Commits are checkpoints and it's trivial (esp. with AI-assisted CLI) to roll things back if needed. Workflow is all about small diffs, with sessions being fine-grained, not about implementing entire features wholesale. Serialize overall plans for feature work as files in the codebase in the interim.
Re:Claude Code: An Agentic cleanroom analysis by gaut on Sunday June 01, 2025 @07:03PM (#44154404)
How is viewing and approving diffs in an editor any less reliable than viewing and approving them through the CLI? It won't make any changes without approval (unless you explicitly grant it auto-approval).
Re:Claude Code: An Agentic cleanroom analysis by insane_dreamer on Sunday June 01, 2025 @09:50PM (#44155225)
Before that it showed you diffs in the console, which worked ok.

Claude Code now also has a PyCharm plugin (and probably other JetBrains IDEs) that also shows you diffs in the pycharm editor.

Re:Claude Code: An Agentic cleanroom analysis by bananapub on Wednesday June 04, 2025 @08:54AM (#44180234)
claude code churns away in a terminal, I have the git repository open in emacs with auto-revert-mode enabled so it reloads files if they're changed under it.

I view the files, and then review the changes in magit, and either approve some or all of them and commit them, or tell claude to do some thing else.

it works astonishingly well.

Re:Claude Code: An Agentic cleanroom analysis by scuff3d on Sunday June 01, 2025 @07:12PM (#44154465)
If this is what software engineering is going to become I'm finding a new job.
Re:Claude Code: An Agentic cleanroom analysis by elliotec on Sunday June 01, 2025 @07:28PM (#44154546)
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 done in two nights than I did in 3 months.

I’m sure there are tons of arguments and great points against what I just said, but it’s my current reality and I still can’t believe it. I shelled out the $100/mo after one night of blowing through the $20 credits I used as a trial.

It does struggle with design and front end. But don’t we all.

Re:Claude Code: An Agentic cleanroom analysis by petetnt on Sunday June 01, 2025 @07:44PM (#44154636)
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 by elliotec on Sunday June 01, 2025 @09:18PM (#44155070)
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.

Re:Claude Code: An Agentic cleanroom analysis by john2x on Sunday June 01, 2025 @07:40PM (#44154610)
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 by scuff3d on Sunday June 01, 2025 @10:23PM (#44155366)
Hit me up when you release your product. I keep seeing stuff like this and never see any proof. Companies aren't releasing 10x the features/patches/bug fixes/products, open source isn't getting 10x the number of quality PRs, absolutely no real evidence that the massive productivity gains actually exist.

What I've seen is people feel more productive, until the reality of all the subtle problems start to set in. Even skilled engineers usually only end up with 10 or 20% productivity gains by the time they reduce its usecase to where it's actually not total dog shit, or by the time they go back around and fix all the problems.

The highest quality product I know of where the creator has talked about his use of AI is ghostty, and he's not claiming massive improvements, just that it's definitely helpful.

Re:Claude Code: An Agentic cleanroom analysis by elliotec on Monday June 02, 2025 @02:03AM (#44156153)
I’ll happily let you know when I release. Goal date for public beta is the 15th. I’d love eyes and feedback on it ASAP.

Hopefully it’s obvious that Claude will not have simply written the entire thing but you might get a sense of what it can do quickly as part of a whole - maybe similar to your last sentence but I suppose I am claiming massive improvements (in productivity, no warranty on quality yet).

Also keep in mind I’m entirely solo here. I fully agree with your points that the proof is in the pudding and obviously there’s nuance to all of it. But yeah, I’m not exaggerating with my commentary above.

Re:Claude Code: An Agentic cleanroom analysis by scuff3d on Monday June 02, 2025 @03:16AM (#44156412)
If you don't mind me asking a couple questions, what percentage of your code would you say is AI generated, meaning you promoted an AI and it went off and wrote code that you used (with or without modification)?

And how much time would you say you spend wrangling the AI, meaning either repromting or substantially editing what you get back?

Re:Claude Code: An Agentic cleanroom analysis by shostack on Sunday June 01, 2025 @07:29PM (#44154550)
What are some examples of agents you've created that you regularly use?
Re:Claude Code: An Agentic cleanroom analysis by rane on Sunday June 01, 2025 @06:14PM (#44154132)
Have you been able to interface Claude Code with Gemini 2.5 Pro? I'm finding that Gemini 2.5 Pro is still better at solving certain problems and architecture and it would be great to be able to consult directly in CC.
Re:Claude Code: An Agentic cleanroom analysis by ramoz on Sunday June 01, 2025 @07:28PM (#44154547)
I do it indirectly. Gemini is my architecture goto. Claude Code for execution. It's just way more efficient to feed large portions of codebase at once to Gemini, pump out a plan and feed it to Claude Code. https://x.com/backnotprop/status/1929020702453100794
Re:Claude Code: An Agentic cleanroom analysis by SparkyMcUnicorn on Monday June 02, 2025 @01:33AM (#44156051)
My most recent flow is very similar, but I use AiderDesk[0] instead of Prompt Tower for easier creation/editing of plan files.

AiderDesk lets you save snapshots of a point in time, so I create "presets" to restore sets of context files and/or conversation history (you can restore one or both), which is a really nice bonus. You can also add/remove context as needed without the manual copy/pasting work when I forget to include something or accidentally included too much. Its VS Code extension makes adding/removing files from context seamless.

[0] https://github.com/hotovo/aider-desk

Re:Claude Code: An Agentic cleanroom analysis by triyambakam on Sunday June 01, 2025 @06:22PM (#44154188)
Well a quick hack is to tell Claude Code to make "AI!" comments in the code which Aider can be configured to watch for, then Gemini 2.5 Pro can do those tasks. Yes I really like Gemini still too