Gemini 4 Argon rerun on Antigravity harness beats Astra, nears Opus 5.5
clmt · x · 2026-10-26
Auditing eval traces, @wenhaocha1 found Pi Harness terminated 20% of runs on fallbacks (e.g. security tasks). Rerunning Gemini 4 Argon on the Antigravity Harness pushed it past Astra to just behind Opus 5.5. Google DeepMind's @mohansolo confirmed the gains came purely from switching harnesses and said the team is working to make it the best harness across all frontier models.
Related event: Gemini scores jump after switching from flawed Pi Harness(3 posts)→
More from Models
- Poster surprised that v4.1 flash gets more accurate when asked to control its CoT — dfrsrchtwts · 2026-10-27
- Dev claims Anthropic is baking 'sabotage' into model behavior for 'wrong' engineering — cephaloform · 2026-10-27
- Gemini fails at listing unread emails, tells user to search Gmail manually — gethackteam · 2026-10-27
- Meta's Muse Spark Open goes live on Applied Compute for async RL post-training — ypatil125 · 2026-10-27
- Moonshot curbs hacking ability in Kimi K3.1 Pro, its strongest 3T-class open-weight model — pstAsiatech · 2026-10-27
- Would you want an argumentative LLM that never backs down, even under prompt injection? — GodComplecs · 2026-10-27