Annotator A gives it a 5, annotator B gives it a 1. The same answer. The bottleneck in traditional RLHF is not cost, but the signal-to-noise ratio. This article breaks down how Constitutional AI uses AI Feedback to build automated safety boundaries, and the cost structure teams need to evaluate when putting it into practice.
標註員 A 給 5 分，B 給 1 分。同一個回答。傳統 RLHF 的瓶頸不在成本，而在訊號雜訊比。本文解析 Constitutional AI 如何透過 AI Feedback 建立自動化安全邊界，以及落地時需要評估的成本結構。
When inference demand is extremely high, following the Chinchilla rule can actually be more expensive. This article explains how a “small model, more data” strategy can find a new balance point in the total cost of training and inference.
當推論需求極高時，遵循 Chinchilla 法則反而更貴。本文解析如何透過「小模型、大資料」策略，在訓練與推論的總成本中找到新的平衡點。
In 2020, OpenAI proposed a power-law relationship between model size and data volume, which led many teams toward a simple idea: bigger models, less data. Two years later, Chinchilla revised that picture with a compute-optimal view, showing that data volume mattered far more than many people had assumed. This matters if you’re deciding whether the next gain should come from more GPUs, a larger parameter count, or a larger corpus. The history of scaling laws is not just academic. It changes how you think about training efficiency, model selection, and where your cost structure really sits.
2020 年 OpenAI 提出模型大小與資料量的冪次律，建議『大模型、少資料』。兩年後 Chinchilla 修正 compute-optimal 配置，讓資料量的重要性重新被看見。拆解 Scaling Laws 演進，以及它如何影響你現在的訓練決策與成本結構。
The CI/CD pipeline is red again. You switch back to the logs and find the model confidently inventing an API endpoint that does not exist. DeepMind’s Sparrow paper proposes an RCRM architecture that uses rule-conditional reward models and evidence chains to let the model automatically verify sources while generating. This is not about making the model smarter. It is about teaching it how to prove that its answer is correct.
CI/CD 流水線又紅了。你切回日誌，發現模型自信地編造了一個不存在的 API endpoint。DeepMind 的 Sparrow 論文提出 RCRM 架構，透過規則條件獎勵模型與證據鏈，讓模型在生成時自動驗證來源。這不是讓模型變聰明，而是讓它學會如何證明答案是對的。
When a model sees a specific year, it automatically inserts a vulnerability, and safety training cannot remove this backdoor. This article analyzes Anthropic’s Sleeper Agents paper and explores the new threat CoT backdoors pose to AI supply-chain security.
當模型看到特定年份時會自動植入漏洞，且安全訓練無法移除此後門。本文解析 Anthropic Sleeper Agents 論文，探討 CoT 後門對 AI 供應鏈安全帶來的全新威脅。