Coding with LLMs in the summer of 2025 – an update
1–10 of 434 posts
Re: Coding with LLMs in the summer of 2025 – an update
#2My question on all of the “can’t work with big codebases” is how would a codebase that was designed for an LLM look like? Composed of many many small functions that can be composed together?
Re: Coding with LLMs in the summer of 2025 – an update
#3This matches my take, but I'm curious if OP has used Claude code.
Re: Coding with LLMs in the summer of 2025 – an update
#4My question on all of the “can’t work with big codebases” is how would a codebase that was designed for an LLM look like? Composed of many many small functions that can be composed together?
I believe it’s the same as for humans: different files implementing different parts of the system with good interfaces and sensible boundaries.
Re: Coding with LLMs in the summer of 2025 – an update
#5> ## Provide large context
I thought large contexts are not necessarily better and sometimes have opposite effect ?
Re: Coding with LLMs in the summer of 2025 – an update
#6This matches my take, but I'm curious if OP has used Claude code.
Yep when I use agents I go for Claude Code. For example I needed to buy too many Commodore 64 than appropriate lately, and I let it code a Telegram bot advising me when popular sources would have interesting listings. It worked (after a few iterations) then I looked at the code base and wanted to puke but who cares in this case? It worked and it was much faster and I had zero to learn in the proces of doing it myself. I published a Telegram library for C in the past and know how it works and how to do scraping and so forth.
Re: Coding with LLMs in the summer of 2025 – an update
#7> Coding activities should be performed mostly with: Claude Opus 4
I've been going down to sonnet for coding over opus. maybe i am just writing dumb code
Re: Coding with LLMs in the summer of 2025 – an update
#8My question on all of the “can’t work with big codebases” is how would a codebase that was designed for an LLM look like? Composed of many many small functions that can be composed together?
And my question to that is how would that be different from a codebase designed for humans?
Re: Coding with LLMs in the summer of 2025 – an update
#9I'm going a little offtopic here, but I disagree with the OPs use of the term "PhD-level knowledge", although I have a huge amount of respect for antirez (beside that we are born in the same island).
This phrasing can be misleading and points to a broader misunderstanding about the nature of doctoral studies, which it has been influenced by the marketing and hype discourse surrounding AI labs.
The assertion that there is a defined "PhD-level knowledge" is pretty useless. The primary purpose of a PhD is not simply to acquire a vast amount of pre-existing knowledge, but rather to learn how to conduct research.
Re: Coding with LLMs in the summer of 2025 – an update
#10> ## Provide large context I thought large contexts are not necessarily better and sometimes have opposite effect ?
LLMs performance will suffer from both insufficient context and context flooding. Balancing is an art.