Claude Code is unusable for complex engineering tasks with the Feb updates

Re:Claude Code is unusable for complex engineering tasks wit... by frog437 on Monday April 06, 2026 @09:17PM (#47669568)

depending on how large your codebase is, hopefully not. At this point use something like the IX plugin to ingest codebase and track context, rather than from the LLM itself.

[ Parent | on HN ]

Re:Claude Code is unusable for complex engineering tasks wit... by frog437 on Tuesday April 07, 2026 @12:04AM (#47670632)

This is crazy..

tokensSaved = naiveTokens - actualTokens

  - naiveTokens = 19.4M — what ix estimates it would have cost to answer your queries without graph intelligence (i.e., dumping full files/directories into context)                                    
  - actualTokens = 4.7M — what ix's targeted, graph-aware responses actually used
  - tokensSaved = 14.7M — the difference

[ Parent | on HN ]

Re:Claude Code is unusable for complex engineering tasks wit... by andoando on Thursday April 09, 2026 @12:14AM (#47699197)

I mean whatever part of the code that is read by the AI has to be in the content window at some point or another nSprewd throughout your sessions Id think even with a huge codebase, 90% of it is going to be there

[ Parent | on HN ]