Claude
频道 @anthropicai
Anthropic is an AI safety and research company that’s working to build reliable, interpretable, steerable AI systems, and the creators of the Claude Chat Bot Assistant.
评分(满分 10) 4.6 评分(满分 10) 4.6 /10 系统评分 · 评分说明
- 订阅者
- 806
- 最近发帖
- 1 年前
资料采集于 2026-11-21 · 非实时
简介
Anthropic is an AI safety and research company that’s working to build reliable, interpretable, steerable AI systems, and the creators of the Claude Chat Bot Assistant.
查看 Telegram 上的原始简介
Anthropic is an AI safety and research company that’s working to build reliable, interpretable, steerable AI systems, and the creators of the Claude Chat Bot Assistant.
评分构成
算法 v1 · 评分说明系统基础分 4.6(1 + 维度贡献 3.56) · 最终 4.6
维度 输入 维度值 权重 贡献
内容质量 未经判官审核 (按中性值 0.5 计) · 40% 0.50 40% +1.80
安全风险 未经判官审核 (按中性值 0.5 计) · 30% 0.50 30% +1.35
受众规模 806 订阅者 · 12% 0.30 12% +0.32
近期活跃 最近发帖 1 年前 · 10% 0.10 10% +0.09
Telegram 认证 无认证 · 4% 0.00 4% —
官网互链 无关联工具 · 4% 0.00 4% —
近期动态
在 Telegram 查看全部Channel name was changed to «Claude»
[图片/视频]
1.1 万 次浏览
Models struggle to transition between these strategies, as exhibited by a spike in test loss. This spike moves to larger datasets as one increases model capacity. This is a clear signature of double-descent, a phenomenon that is now well-known in the ML literature.
We hope these results are a step towards a mechanistic theory of memorization. There are many open questions, such as understanding the loss spike, or what happens when only a subset of the data is repeated.
Thanks to Adam Jermyn for his comments reproducing and extending these results!
https://transformer-circuits.pub/2023/toy-d…
9,790 次浏览 图片/视频
For small training sets, models use superposition to memorize more data points than the two available neurons. For large training sets, models learn features in superposition, as observed in our previous work, allowing the model to generalize.
https://transformer-circuits.pub/2022/toy_model/index.html
6,910 次浏览 图片/视频
Our prior work showed that these toy models use a strategy called “superposition” to learn more features than available neurons. Here we observe how training data points, as well as features, are embedded in the hidden space.
5,680 次浏览 图片/视频