Show HN: Codex context bloat? 87% avg reduction on SWE-bench Verified traces
Summary not yet generated for this article.
Original Text
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
Comments (2 of ) ⌛