from Hacker News

Claude Code: An Agentic cleanroom analysis

by hrishi on 6/1/25, 7:04 PM with 53 comments

• by thegeomaster on 6/1/25, 10:59 PM

  This is kinda frustrating to read. The style is very busy, and it lacks a clear structure. It's basically an information dump without any acknowledgment of what's important or not. Big-O notation is provided for a lot of operations where you wouldn't really care about Big-O (in a system where calls to an LLM dominate, this is most operations). Big picture story about how Claude Code actually works, as in what happens when I type in a prompt (which I'm very much interested, given how much I use it) is lacking. Some diagrams are so nonsensical they become funny. Look at this: https://southbridge-research.notion.site/Prompt-Engineering-... In general, the prompt engineering page, which deserves maybe the most detailed treatment, is just a dump of prompts and LLM bullet point filler.

  I don't want to be overly negative, but I think it's only fair given the author hasn't graced us with their own thoughts, instead offloading the actual writing to an LLM.

• by triyambakam on 6/1/25, 9:55 PM

  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.

• by InGoldAndGreen on 6/1/25, 10:12 PM

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

• by MoonGhost on 6/1/25, 11:06 PM

  > Your browser is not compatible with Notion. Please upgrade to the latest browser version, or visit our help center for more information.

  FireFox 113.0.2, how come?

• by fullstackchris on 6/1/25, 10:06 PM

  also, i will say, (if we can trust the findings in these notes are relatively accurate of the real implementation) is a PERFECT example of the real level of complexity used in cutting edge configuration of using LLM... its not just some complex fancy prompt you give to a model in a chat window... there is so much important stuff happening behind the scenes... though i suppose the people who complain about LLMs hallucinating / screwing up havent tried claude code or any agentic work flows - or, it could be their architecture / code is so poorly written and poorly organized that even the LLM itself struggles to modify it properly

• by ramoz on 6/1/25, 11:39 PM

  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.

• by owebmaster on 6/1/25, 10:23 PM

  I have nothing against LLM-generated content. But when publishing, make sure the content is displayed correctly and that it is enjoyable to read.

• by 29athrowaway on 6/1/25, 11:13 PM

  If you want an example of a good analytical breakdown of some technology, look at this as an example: https://fabiensanglard.net/quake3/network.php

  It is good because it highlights the relevant aspects of the design and you can use this, plus some other resources, to replicate the idea.

• by fullstackchris on 6/1/25, 9:57 PM

  interesting... the analysis finds that the MCP supports websockets as a transport... when there is big drama going on right now that anthropic said "they will never support that", folks hating SSE, and so on and so forth