DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.

1,180+ deals tracked  ·  22 AI investment memos  ·  Updated daily

← Back to leaderboard

Codex context bloat? 87% avg reduction on SWE

Show HN: Codex context bloat? 87% avg reduction on SWE-bench Verified traces

51 AI Score
Show_hn other Added Apr 24, 2026

Details

Sector
other
Total Funding
$0
Last Round
$0

About

If you had to build a context window manager in 24h, would you stick to the existing model or come up with something better?<p>Here&#x27;s what I did:<p>1. Built a proxy that intercepts Codex&#x27;s calls to OpenAI and rewrites them on the fly.<p>2. Replayed 3,807 rounds of SWE-bench Verified traces through it: avg prompt 44k → 6k tokens (-87%).<p>3. Posted it to HN to get the next reduction applied to my confidence interval — starting with the inevitable &quot;How about accuracy?&quot;<p>npx -y pando-proxy · github.com&#x2F;human-software-us&#x2F;pando-proxy

AI Score Reasoning

The project addresses a critical bottleneck in LLM-based software engineering (token cost and context limits) with impressive initial compression results on SWE-bench. However, it currently lacks market validation, a clear moat against model providers who are expanding context windows natively, and detailed team information.

Source

Show_hn — View original →