conv.

← The whole story
AI
SoL-Pi: Researchers Cut Coding Agent Costs by a Third

Red-teaming study examines blocking classifiers for malign coding agents

1 Sep 18 12:00 AM · 8d ago · 3 articles · 1 source · development 1 of 3

Alex Remedios and colleagues release research on red-teaming auto mode—the production blocking monitors in Claude Code and OpenAI's Codex—testing their robustness when agents are persistently misaligned, not just accidentally harmful.

Red-teaming study examines blocking classifiers for malign coding agents
academy.dair.ai

“Token efficiency therefore becomes important for scaling recursive self-improvement.”

SoL-Pi authors (Haozhe Liu et al.), Researchers · rss ↗

Haozhe Liu Lead researcher, SoL-Pi studyRun-Ze Fan Lead researcher, harness components studyNVIDIA, NTU, MIT Collaborating institutions

The whole story articlespostscomments the bright band is this development · numbered dots are the others · click one to jump

Peak 8 pieces in 3h at Sep 18, 8 AM; 32 pieces over 9 days (8 articles · 12 posts · 12 comments) Sep 17, 8 AM — 1 piece · 1 post — Hacker News 1Sep 17, 11 AM — quietSep 17, 2 PM — quietSep 17, 5 PM — quietSep 17, 8 PM — quietSep 17, 11 PM — 4 pieces · 4 articles — Newswires 4Sep 18, 2 AM — quietSep 18, 5 AM — quietSep 18, 8 AM — 8 pieces · 2 articles · 1 post · 5 comments — Hacker News 6, Newswires 2Sep 18, 11 AM — 5 pieces · 5 comments — Hacker News 5Sep 18, 2 PM — 2 pieces · 2 comments — Hacker News 2Sep 18, 5 PM — 2 pieces · 2 posts — Hacker News 1, Mastodon 1Sep 18, 8 PM — quietSep 18, 11 PM — quietSep 19, 2 AM — quietSep 19, 5 AM — quietSep 19, 8 AM — quietSep 19, 11 AM — quietSep 19, 2 PM — quietSep 19, 5 PM — quietSep 19, 8 PM — quietSep 19, 11 PM — quietSep 20, 2 AM — quietSep 20, 5 AM — quietSep 20, 8 AM — quietSep 20, 11 AM — quietSep 20, 2 PM — quietSep 20, 5 PM — quietSep 20, 8 PM — quietSep 20, 11 PM — quietSep 21, 2 AM — quietSep 21, 5 AM — quietSep 21, 8 AM — quietSep 21, 11 AM — quietSep 21, 2 PM — quietSep 21, 5 PM — quietSep 21, 8 PM — 1 piece · 1 post — Hacker News 1Sep 21, 11 PM — quietSep 22, 2 AM — quietSep 22, 5 AM — 1 piece · 1 post — Hacker News 1Sep 22, 8 AM — quietSep 22, 11 AM — quietSep 22, 2 PM — quietSep 22, 5 PM — quietSep 22, 8 PM — quietSep 22, 11 PM — 2 pieces · 2 articles — Newswires 2Sep 23, 2 AM — 1 piece · 1 post — Hacker News 1Sep 23, 5 AM — quietSep 23, 8 AM — 1 piece · 1 post — Hacker News 1Sep 23, 11 AM — 2 pieces · 2 posts — Hacker News 2Sep 23, 2 PM — quietSep 23, 5 PM — quietSep 23, 8 PM — quietSep 23, 11 PM — quietSep 24, 2 AM — quietSep 24, 5 AM — 2 pieces · 2 posts — Hacker News 2Sep 24, 8 AM — quietSep 24, 11 AM — quietSep 24, 2 PM — quietSep 24, 5 PM — quietSep 24, 8 PM — quietSep 24, 11 PM — quietYesterday, 2 AM — quietYesterday, 5 AM — quietYesterday, 8 AM — quietYesterday, 11 AM — quietYesterday, 2 PM — quietYesterday, 5 PM — quietYesterday, 8 PM — quietYesterday, 11 PM — quietToday, 2 AM — quietToday, 5 AM — quietToday, 8 AM — quietToday, 11 AM — quietToday, 2 PM — quiet 123
1Red-teaming study examines blocking…2Research community discusses harness…3SoL-Pi findings show 44–49% token…
Sep 18Sep 19Sep 20Sep 21Sep 22Sep 23Sep 24yesterdaynow · 3:39 PM ET

What was reported 2 claims about this development

  1. 3 outlets An empirical study of harness design for coding agents

    first by HN Best, 8d ago · also HN Frontpage, arXiv cs.AI

  2. 1 outlet Red-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents

    first by arXiv cs.AI, 8d ago

All 3 developments of SoL-Pi: Researchers Cut Coding Agent Costs by a Third →

Hacker NewsNewswiresMastodon