跳到正文
Andrew Curran· @AndrewCurran_ · X·· 5 小时前AI 评分22
AI 导读

GPT-2至GPT-4的困惑度从4降至约0.91,伴随上下文学习、流畅对话及链式推理等能力的逐步显现。当前模型损失已低于0.8,在网络安全和数学领域展现出变革性能力。这些能力并非预先可知,而是该单一指标进步带来的涌现潜能。

正文 · 原文

'The range of capabilities of models that are largely described by this one metric is stunning. Setting the new perplexity state-of-the-art on older datasets4, GPT‑2 was arguably the first model capable of consistently formulating coherent paragraphs of text. The next major leap, GPT‑3, was capable of learning in context, given a few examples of a task. GPT‑3.5, at a log-perplexity of ~0.99 on our current main evaluation dataset, was capable of fluent conversation and formed the basis for the original ChatGPT. GPT‑4, at ~0.91, was proficient at utilizing chain-of-thought reasoning productively, which motivated the subsequent targeted elicitation of this capability and the creation of modern reasoning models. Now, as we have reached losses below 0.8, we have seen the emergence of transformative capabilities in fields like cybersecurity and mathematics. I want to reemphasize that it was not at all clear a priori that these capabilities would appear once those precise perplexity thresholds are met - they can fundamentally be seen as emergent latent capabilities from progress on this one metric.'

来源:Andrew Curran · x.com