HN Explorer

Show HN: Codex context bloat? 87% avg reduction on SWE-bench Verified traces (npmjs.com)

10 points by george_ciobanu ↗ HN
If you had to build a context window manager in 24h, would you stick to the existing model or come up with something better?

Here's what I did:

1. Built a proxy that intercepts Codex's calls to OpenAI and rewrites them on the fly.

2. Replayed 3,807 rounds of SWE-bench Verified traces through it: avg prompt 44k → 6k tokens (-87%).

3. Posted it to HN to get the next reduction applied to my confidence interval — starting with the inevitable "How about accuracy?"

npx -y pando-proxy · github.com/human-software-us/pando-proxy

1 comment

[ 2.9 ms ] story [ 9.6 ms ] thread
camelliaPTM
The prompt went from 44k to 6k tokens, but you're making two extra model calls per round to get there (chunker + working_memory_update). What does the all-in cost comparison actually look like?