In the largest survey of its kind, 2,778 researchers who had published in
top-tier artificial intelligence (AI) venues gave predictions on the pace of AI
progress and the nature and impacts of advanced AI systems The aggregate
forecasts give at least a 50% chance of AI systems achieving several milestones
by 2028, including autonomously constructing a payment processing site from
scratch, creating a song indistinguishable from a new song by a popular
musician, and autonomously downloading and fine-tuning a large language model.
If science continues undisrupted, the chance of unaided machines outperforming
humans in every possible task was estimated at 10% by 2027, and 50% by 2047.
The latter estimate is 13 years earlier than that reached in a similar survey
we conducted only one year earlier [Grace et al., 2022]. However, the chance of
all human occupations becoming fully automatable was forecast to reach 10% by
2037, and 50% as late as 2116 (compared to 2164 in the 2022 survey).
Most respondents expressed substantial uncertainty about the long-term value
of AI progress: While 68.3% thought good outcomes from superhuman AI are more
likely than bad, of these net optimists 48% gave at least a 5% chance of
extremely bad outcomes such as human extinction, and 59% of net pessimists gave
5% or more to extremely good outcomes. Between 38% and 51% of respondents gave
at least a 10% chance to advanced AI leading to outcomes as bad as human
extinction. More than half suggested that "substantial" or "extreme" concern is
warranted about six different AI-related scenarios, including misinformation,
authoritarian control, and inequality. There was disagreement about whether
faster or slower AI progress would be better for the future of humanity.
However, there was broad agreement that research aimed at minimizing potential
risks from AI systems ought to be prioritized more.

在最大规模的调查中，2778 名在顶级人工智能（AI）期刊发表过论文的研究人员对 AI 进展的速度、高级 AI 系统的性质和影响做出了预测。总体预测显示，到 2028 年，AI 系统有至少 50% 的机会实现几个里程碑，包括自主构建支付处理网站、创建一首无法与热门音乐家的新歌区分的歌曲，以及自主下载和微调大规模语言模型。如果科学持续稳定发展，到 2027 年，无需人类援助的机器在任何可能的任务上超越人类的机会被估计为 10%，到 2047 年概率达到 50%。然而，所有人类职业完全可自动化的机会预计将在 2037 年达到 10%，最迟到 2116 年达到 50%（相比于 2022 年调查的 2164 年）。大多数受访者对 AI 进展的长期价值表示了相当大的不确定性：虽然 68.3% 的人认为超人级 AI 有更多好的结局可能性，但在这些净乐观主义者中，48% 认为极坏的结果（如人类灭绝）至少有 5% 的机会，而 59% 的净悲观主义者给出了至少 5% 的机会，以至于产生极好的结果。在回答关于 AI 的六种不同情景（包括错误信息、权威控制和不平等等）是否应引起 “大量” 或 “极大” 关注的问题时，超过一半的受访者表示同意。关于快速或缓慢的 AI 进展对人类未来更好的观点存在分歧。然而，有广泛的共识认为应优先考虑旨在最小化 AI 系统潜在风险的研究。

AI 未来上的数千名 AI 作者

Thousands of AI Authors on the Future of AI

Humankind is entering a novel creative era in which anybody can synthesize
digital information using generative artificial intelligence (AI).
Text-to-image generation, in particular, has become vastly popular and millions
of practitioners produce AI-generated images and AI art online. This chapter
first gives an overview of the key developments that enabled a healthy
co-creative online ecosystem around text-to-image generation to rapidly emerge,
followed by a high-level description of key elements in this ecosystem. A
particular focus is placed on prompt engineering, a creative practice that has
been embraced by the AI art community. It is then argued that the emerging
co-creative ecosystem constitutes an intelligent system on its own - a system
that both supports human creativity, but also potentially entraps future
generations and limits future development efforts in AI. The chapter discusses
the potential risks and dangers of cultivating this co-creative ecosystem, such
as the bias inherent in today's training data, potential quality degradation in
future image generation systems due to synthetic data becoming common place,
and the potential long-term effects of text-to-image generation on people's
imagination, ambitions, and development.

这篇研究论文探讨了人工智能生成图像的创作方式以及弊端，如训练数据的偏见、合成数据常态化可能导致未来图像生成系统的质量下降，以及文本生成图像对人们想象力、抱负和发展的潜在长期影响。

文本到图像生成的培育实践

The Cultivated Practices of Text-to-Image Generation

Property inference attacks reveal statistical properties about a training set
but are difficult to distinguish from the primary purposes of statistical
machine learning, which is to produce models that capture statistical
properties about a distribution. Motivated by Yeom et al.'s membership
inference framework, we propose a formal and generic definition of property
inference attacks. The proposed notion describes attacks that can distinguish
between possible training distributions, extending beyond previous property
inference attacks that infer the ratio of a particular type of data in the
training data set. In this paper, we show how our definition captures previous
property inference attacks as well as a new attack that reveals the average
degree of nodes of a training graph and report on experiments giving insight
into the potential risks of property inference attacks.

本文提出了一种形式化且通用的财产推断攻击定义，该定义描述能够区分可能的训练分布的攻击，并展示了如何将先前的财产推断攻击和新的攻击捕获在该定义中，并为揭示潜在风险的实验提供了见解。