News for hackers. Stuff that matters.

A comment on Are LLMs not getting better?. Parent comment

Re:Are LLMs not getting better? by naruhodo on Thursday March 12, 2026 @11:51PM (#47360491)
> 1) Something happened during 2025 that made the models (or crucially, the wrapping terminal-based apps like Claude Code or Codex) much better. I only type in the terminal anymore.

I have heard say that the change was better context management and compression.

[ Parent | on HN ]
Re:Are LLMs not getting better? by bbatha on Friday March 13, 2026 @12:46AM (#47360780)
A lot of enhancements came on the model side which in many ways enabled context engineering.

200k and now 1M contexts. Better context management was enabled by improvements in structured outputs/tool calling at the model level. Also reasoning models really upped the game “plan” mode wouldn’t work well without them.

[ Parent | on HN ]