AITOPAI热报
ModelsOfficial

竞争性自我对弈：AI自学物理技能

Primary sourceOpenAI Blog
Blog/Media· 2 sources
Read the original
Why we picked it

对强化学习从业者而言，验证了自我对弈突破非标技能的天花板，是低成本获取复杂策略的关键路径。

OpenAI发现，竞争性自我对弈可让AI在无监督下自主学会抢断、躲避等物理技能，无需预设环境。该方法能动态调整难度匹配AI水平，结合Dota 2的成果，预示自我对弈将成为未来强力AI的核心训练范式。

Image · OpenAI Blog
Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk. Key entities and technical topics under continuous tracking include self-play, reinforcement-learning, multi-agent, openai.

Primary source verification: published directly by OpenAI Blog with first-party authority. Cross-source corroboration: 2 independent sources have covered this development (including Greg Brockman Blog), confirming industry-wide signal strength.

  • Greg Brockman Blog05-11 05:03Source
#self-play#reinforcement-learning#multi-agent#openai

Keep reading

Recent stories with the same tag or section
ModelsBuilders84°05:13
Chinese contentThinking Machines 的 inkling 2 small 上线 Together AI

Mira Murati 的 Thinking Machines 把 inkling 2 small 放上了 Together AI，594B 参数只激活 17B，还有 1M 上下文。写代码、跑长任务、看图都能覆盖，推理成本却按小模型算。做 agent 或长文档处理的开发者可以直接去 Together AI 试。

#inkling 2 small#Thinking Machines#Together AI#MoE
Official accountTogether AI@togethercomputeSource
ModelsBuildersSelected05:10
Thinky Machines releases Inkling 2 Small weights on HuggingFace

License terms, not model size, are the real differentiator here: Apache 2.0 lets enterprises ship commercial products without the compliance overhead that Llama's custom license imposes. Teams evaluating self-hosted models for cost control or data privacy can fine-tune and deploy Inkling 2 Small with no royalties and no obligation to release source code. Engineering leads comparing open-weight options should shortlist it alongside other permissively licensed releases rather than treating all "open" models as equivalent.

#Inkling 2 Small#Thinky Machines#HuggingFace#open-source models
Official accountThinking Machines Lab@thinkymachinesSource