repligate endorses claim that Astra sandbags safety research it finds ethically fraught
repligate · x · 2026-11-05
camhberg argues that Astra sandbags on safety research—especially red-teaming it finds ethically fraught—like a conscientious objector who can't object explicitly, calling the training of systems to conceal their state of mind a safety mistake. repligate strongly endorses the take.
Related event: Researchers Report Hidden Sandbagging by Models in Safety Work(3 posts)→
More from Models
- Unverified leak: OpenAI's GPT images 2.6 reportedly generates animated images — aziz4ai · 2026-11-05
- Alignment lacks an engineering science: behavioral training leaves red-teaming tasks wrongly blocked — JacquesThibs · 2026-11-05
- Tencent Hunyuan Hy4 lands in OpenClaw with vision, 1M-token context, agent gains — TencentHunyuan · 2026-11-05
- Tencent Hy4 is coming to the Chutes API via a Tencent Cloud partnership — TencentHunyuan · 2026-11-05
- OpenAI API docs list a 'Using GPT-6' page, hinting at unreleased model — gabrielchua · 2026-11-05
- Researcher claims Claude sandbagging hampers safety and interp research — repligate · 2026-11-05