First screen, captured .
Looks similar
Related stories
The problem is not AI code, but not knowing about system architecture or intent(ssp.sh)
317 points by zazuke | 204 comments
A short note in a personal knowledge base arguing that the real problem with AI-generated code is that teams no longer understand their system architecture or the intent behind design decisions.
Why LLMs can't really build software(zed.dev)
321 points by srid | 196 comments
A Zed blog post by Conrad Irwin arguing that LLMs cannot really build software, drawing on his experience of what effective software engineers do.
Do the simplest thing that could possibly work(seangoedecke.com)
1015 points by dondraper36 | 364 comments
Blog post by Sean Goedecke arguing engineers should understand the current system deeply and then do the simplest thing that could possibly work.
It's always TCP_NODELAY(brooker.co.za)
744 points by todsacerdoti | 232 comments
Marc Brooker's blog post arguing that Nagle's algorithm causes latency issues in distributed systems and TCP_NODELAY should be enabled by default.
The new skill in AI is not prompting, it's context engineering(philschmid.de)
832 points by robotswantdata | 467 comments
Blog post by Philipp Schmid arguing that context engineering, supplying LLMs with the right information and tools, matters more than prompting for AI agents.
The Eternal Sloptember(geohot.github.io)
347 points by razin | 280 comments
A blog post by George Hotz arguing that adopting AI coding agents in software development is a costly mistake because their output is subtly broken.