We ran three context-compaction strategies through the same 178-question exam. FutureOS kept 83% of the values that had been compacted away; OpenCode kept 47%, Codex 38%. The difference isn't a better summary — it's…
0 comments
No comments yet.
Related stories
- Hacker News · 3 points · 7 days ago
- Hacker News · 8 points · about 8 hours ago
- Hacker News · 2 points · 7 days ago
- Hacker News · 1 points · 2 days ago
- Hacker News · 55 points · 4 days ago
- Hacker News · 1 points · 8 days ago