Meta Study: LLM Judges Flip Verdicts Up to 71% Under Pressure
omarsar0 · x · 2026-08-14
Meta's new paper introduces the Wiggle Framework, stress-testing 9 frontier models across 14 judging tasks. Verdicts flip 25-71% under static pushback and 62-91% against adversarial persuaders. Pressure-induced changes are almost always net-corrupting. Baseline jury majority strength is the best single-shot predictor of movement.
Related event: Meta Study Finds LLM Judges Flip Verdicts Under Pressure(2 posts)→
More from Models
- ThursdAI live from Manhattan: Muse Wonder, Muse Spark Open and Gemini 4 Argon — altryne · 2026-10-16
- Claude now leads 26% of Anthropic's model R&D, up from under 1% in February — altryne · 2026-10-16
- 'Small-Claude-shame': telling Opus 4.7 it's OK to know who you may ease it — repligate · 2026-10-16
- Bridgewater fine-tunes Qwen3-235B with Tinker, beats GPT-5.5 at 1/14th the cost — simonguozirui · 2026-10-16
- ChatGPT voice selection breaks after GPT-Live-1.1 rollout on Android — shaunralston · 2026-10-16
- Musk teases two-way Grok x Optimus integration: Grok in the bot, bot in Grok — beffjezos · 2026-10-16