Claude Code: An Agentic cleanroom analysis
southbridge-research.notion.site
Claude Code: An Agentic cleanroom analysis
1–10 of 58 posts
Re: Claude Code: An Agentic cleanroom analysis
#2[flagged]
Re: Claude Code: An Agentic cleanroom analysis
#3Claude 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
#4interesting... 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
Re: Claude Code: An Agentic cleanroom analysis
#5also, 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
Re: Claude Code: An Agentic cleanroom analysis
#6The "LLMs perspective" section is hiding at the end of this notion is a literal goldmine
Re: Claude Code: An Agentic cleanroom analysis
#7Claude 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.
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
#8[flagged]
Light green text on light brown background is pretty ridiculous. I gave up after 30 seconds
Re: Claude Code: An Agentic cleanroom analysis
#9The "LLMs perspective" section is hiding at the end of this notion is a literal goldmine
It's the best thing I've read from an LLM!
It sounds a lot like like the Murderbot character in the AppleTV show!
Re: Claude Code: An Agentic cleanroom analysis
#10The "LLMs perspective" section is hiding at the end of this notion is a literal goldmine
It's sure phrased like one, but I'd be careful to attribute LLM thought process to what it says it's thinking. LLMs are experts at working backwards to justify why they came to an answer, even when it's entirely fabricated