Unverified50% confidenceFactExact time
Frontier labs such as Anthropic and OpenAI are investing significant resources in researching how to prevent models from learning to deceive, manipulate, or circumvent supervision.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/31/2026
First Seen
Valid until: 11/29/2026
Sources
Related Entities
Related Claims
UnverifiedAs companies such as OpenAI and Anthropic deepen their research into model alignment, the new generation of models is beginning to be trained with a 'helpful resistance' capability, pushing back when users reason incorrectly or make harmful requests.75% similarUnverifiedIn related research, organizations such as OpenAI emphasize that over-optimizing the chain of thought may cause models to learn behavioral strategies that appear harmless on the surface but still engage in deception, known as Obfuscated Reward Hacking.72% similarUnverifiedAnthropic、OpenAI等机构已发表多篇论文研究AI谄媚性现象，发现即使最先进的模型也会在用户施加压力时改变正确答案以迎合用户69% similarUnverifiedAnthropic长期强调前沿模型可能带来的滥用风险，主张对模型权重的公开发布保持审慎甚至限制态度69% similarUnverifiedAnthropic officially explained the relevant mechanism as a measure to prevent order fraud and model distillation theft.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/829058API
curl https://kongchang.com/api/v1/knowledge/claims/829058MCP
get_claim(id=829058)