我们有几项重大公告，以来的两个月内涵盖了新的发展2017年战略更新:
1. 5月30日，我们收到了一个惊喜$1.01 million donation从A.以外的加密货币投资者。这是我们通过大幅度收到的最大贡献，并将对我们在来年的计划产生重大影响。
2.两个新的全日制研究人员亚博体育官网加入米IRI: Tsvi Benson-Tilsen and Abram Demski. This comes in the wake of Sam Eisenstat and Marcello Herreshoff’s addition to the team在五月。我们还开始与工程师正常工作，以获得我们新的石板的试用software engineer job openings。
3.我们的两位研究人员最近亚博体育官网离开了：Patrick Lavictoire和Jessica Taylor，研究人员以前亚博体育官网正在寻找我们的工作“高级机器学习系统对齐亚博体育苹果app官方下载“研亚博体育官网究议程。
有关详细信息，请参阅下文。
1. Fundraising
我们在5月底收到的主要捐款总额为1,006,549美元，来自一位长期支持者，他们多年来捐赠了大约50美元的研究计划。亚博体育官网yabo体育官网下载ios该支持者要求继续保持匿名。
今年上半年在Miri的筹款历史上最为成功，其他值得注意的贡献，包括投资者Eric Rogstad的Evereum捐款总计〜22,000美元，捐赠〜$ 67KOctane AIco-founder Leif K-Brooks as part of a Facebook Reactions challenge. In total we’ve raised about $1.45M in the first half of 2017.
We’re thrilled and extremely grateful for this show of support. This fundraising success has increased our runway to around 18–20 months, giving us more leeway to trial potential hires and focus on our research and outreach priorities this year.
具体地说，我们已经制定了几项计划调整，包括：
- 向全职研究员雇用的更加信心，亚博体育官网
- trialing more software engineers, and
- deciding to run only one fundraiser this year, in the winter.1
这可能是一次性异常捐赠，类似于我们从2013 - 2014年从涟漪开发人员Jed Mccaleber收到的加密货币捐赠中的631美元。2期待我们未来两年的资助目标：
- While we still have some uncertainty about our 2018 budget, our current point estimate is roughly$2.5M。
- 今年，在开放慈善项目的支持下，生命研究所的未来和其他来源，我们希望至少在筹资时间内收到至少600万美元的价格。
- Our tentative (ambitious) goal for the rest of the year is to raise额外的$ 950k，或总共300万美元。对于我们的2018年预算来说，这也是足够的，即使我们比预期更快地扩展了我们的工程团队，并会给我们一些缓冲区来解释我们未来的筹款中的不确定性（特别是公开慈善项目是否会继续存在不确定性2017年后支持）。
在为期五年的时间尺度，我们的广泛资金目标是：3
- On the low end, once we finish growing our team over the course of a few years, our default expectation is that our operational costs will be roughly $4M per year, mostly supporting researcher and engineer salaries. Our goal is therefore to reach that level in a sustainable, stable way.
- 在高端，可以想象涉及我们的资金量增加量的情景，在这种情况下，我们将制定一个定性不同的融资目标，反映了我们最有可能基本上重组的事实。
- For funding levels in between—roughly $4M–$10M per year—it is likely that we would not expand our current operations further. Instead, we might fund work outside of our current research after considering how well-positioned we appear to be to identify and fund various projects, including MIRI-external projects. While we consider it reasonably likely that we are in a good position for this, we would instead recommend that donors direct additional donations elsewhere if we ended up concluding that our donors (or other organizations) are in a better position than we are to respond to surprise funding opportunities in the AI alignment space.4
A new major once-off donation at the $1M level like this one covers nearly half of our current annual budget, which makes a substantial difference to our one- and two-year plans. Our five-year plans are largely based on assumptions about multiple-yearfunding flows, so how aggressively we decide to plan our growth in response to this new donation depends largely on whether we can sustainably raise funds at the level of the above goal in future years (e.g., it depends on whether and how other donors change their level of support in response).
To reduce the uncertainty going into our expansion decisions, we’re encouraging more of our regular donors to sign up foryabo体育官网下载ios 或其他经常发出的时间表 - 我们的收入的10％以下来自此类捐款，这限制了我们的规划能力。5We also encourage supporters toreach out to us关于他们未来的捐赠计划，以便我们可以回答问题并制定更具体的具体和雄心勃勃的计划。
2.新雇用
与此同时，两位新的全日制研究人员正在加入我们的团队，在此前亚博体育官网在基于其他机构的同时担任员工。
Abram Demski.谁加入Miri本月作为研究员的研究，正在南加州大学完成亚博体育官网计算机科学博士学位。他对迄今亚博体育官网为止的研究专注于认知架构和人工综合情报。他有兴趣填补正式理论中存在的差距，特别是那些有关人类在推理数学时正在做的事情。
Abram made key contributions to theMirixLOSANGELES.工作了前体导致逻辑诱导。他的其他与miri一起工作包括“决策理论的概括基础“ 和 ”Computable Probability Distributions Which Converge on Believing True Π1句子Will Disbelieve True Π2句子。“
Tsvi benson-tilsen加入Miri作为助理研究员。亚博体育官网Tsvi在芝加哥大学的荣誉中持有BSC，并从UC Berkeley Group留在逻辑和科学博士计划的方法。
在加入Miri的研究人员之前，Tsvi是一个合作亚博体育官网社的“逻辑归纳“ 和 ”正式化收敛工具目标，“也撰写了”用已知的搜索顺序更新的决策理论“ 和 ”Existence of Distributions That Are Expectation-Reflective and Know It。“TSVI的研究亚博体育官网兴趣包括逻辑不确定性，逻辑反应性，以及反思稳定的决策。
我们也接受了我们的前六个软件工程师3个月访问。我们仍在继续审查申请人，鉴于我们最近收到的慷慨支持以及到目前为止，我们可能会审判更多的候选人，而不是以前的计划。
In other news, going forward Scott Garrabrant will be acting as the research lead for MIRI’s代理基础research, handling more of the day-to-day work of coordinating and directing research team efforts.
3. AAMLS议程
我们的AAMLS R亚博体育官网esearch先前是Jessica Taylor，Patrick Lavictoire和Andrew Chritch的重点，所有这些都在2015年中期加入Miri。与帕特里克和杰西卡出发（在良好的条件下）和安德鲁在两年的休假与人类兼容的AI中心一起工作，我们将在来年将相对较少的工作进入Aamls议程。
We continue to see the problems described in the AAMLS agenda as highly important, and expect to reallocate more attention to these problems in the future. Additionally, we see the AAMLS agenda as a good template for identifying safety desiderata and promising alignment problems. However, we did not see enough progress on AAMLS problems over the last year to conclude that we should currently prioritize this line of research over our other work (e.g., our agent foundations research on problems such as logical uncertainty and counterfactual reasoning). As a partial consequence, MIRI’s current research staff do not plan to make AAMLS research a high priority in the near future.
杰西卡，项目领先地区描述了一些在AAML上工作的外卖器：
[...]为什么取得了很少的进展？
[]Difficulty
我认为主要原因是问题非常困难。特别是，它们主要是在“这似乎重要的是”的基础上选择，而不是任何strong直觉可以进行进步。
In comparison, problems in the agent foundations agenda have seen more progress:
- 逻辑不确定性（真理的可定定性，反光奥卡尔，逻辑电感器）
- 决策理论（模态UDT，反射畸形，逻辑电感）
- Vingean反射（模型多态性，逻辑电感器）
有一件事要注意这些问题的是，他们是在强烈的直觉的基础上制定，他们应该是可靠的。在逻辑诱导之前，有可能具有某种渐近方法可以解决限制中许多逻辑不确定性问题。也可以强烈地认为某种自信是可能的。
With problems in the AAMLS agenda, the plausibility argument was something like:
- 以下是问题的现有方法（例如，使用加强信号进行环境目标，或修改此方法）
- Here’s a vague intuition about why it’s possible to do better (e.g. humans do a different thing)
which, empirically, turned out not to make for tractable research problems.
[2.]去喉咙
In an important sense, the AAMLS agenda is “going for the throat” in a way that other agendas (e.g. the agent foundations agenda) are to a lesser extent: it is attempting to solve the whole alignment problem (including goal specification) given access to resources such as powerful reinforcement learning. Thus, the difficulties of the whole alignment problem (e.g. specification of environmental goals) are more exposed in the problems.
[3.]理论与经验主义
Personally, I strongly lean towards preferring theoretical rather than empirical approaches. I don’t know how much I endorse this bias overall for the set of people working on AI safety as a whole, but it is definitely a personal bias of mine.
AAMLS议程中的问题证明，不适合纯粹是理论调查。这可能是因为没有明确的数学美学来确定作为解决方案的算法（例如，对于环境目标问题，实际上并不清楚有关问题的识别数学陈述）。
With the agent foundations agenda, there’s a clearer aesthetic for recognizing good solutions. Most of the problems in the AAMLS agenda have a less-clear aesthetic. […]
有关更多详细信息，请参阅Jessica的回顾关于智能代理基础论坛。
在我们对这些问题的易疏忽达到自信结论之前，需要更多的工作需要进入AAML。但是，缺乏初步进展提供了一些证据，在可能的重大进展之前可能需要新的工具或观点。在来年，我们将继续花一些时间考虑AAMLS，但不会使其成为一个重点。
我们继续与米里研究中积极与安德鲁进行合作，并期望将来与帕特里克和杰西卡一起工作。亚博体育官网Jessica和Andrew特别打算继续关注AI安全研究，包括AI战略和协调的工作。亚博体育官网
我们很感激杰西卡和帕特里克在过去两年中推进了我们的研究计划和我们的组织任务，我就会想念他们两个。亚博体育官网
一般来说，我现在对Miri的立场感到非常好。From our increased financial security and ability to more ambitiously pursue our plans, to the new composition and focus of the research team, the new engineers who are spending time with us, and the growth of the research that they’ll support, things are moving forward quickly and with purpose. Thanks to everyone who has contributed, is contributing, and will contribute in the future to help us do the work here at MIRI.
- 更一般地说，这将使我们能够自信地向我们考虑高优先级的不同研究计划向前迈进，而无需将其他项目中的资源转移，以支持我们的首要任务。亚博体育官网这也应该允许我们在我们2017年更新中提到的目标外展书面上取得更快的进展，因为我们不必在夏季筹款机构上花费员工时间。↩
- 当然，如果这些大型捐款长期看起来像异常值，我们会很高兴。如果读者正在寻找与数字货币有关的事情，他们可能会在最近的浪涌之后持有，知道这一点yabo体育官网下载ios ! In total, MIRI has raised around $1.85M in cryptocurrency donations since mid-2013.↩
- These plans are subject to substantial change. In particular, an important source of variance in our plans is how our new non-public-facing research progresses, where we’re likely to take on more ambitious growth goals if our new work looks like it’s going well.↩
- We would also likely increase our reserves in this scenario, allowing us to better adapt to unexpected circumstances,并且有一个较小的概率，我们将使用这些资金中度增长，而不是目前计划的策略发生重大变化。↩
- 少(如季度)捐款也quite helpful from our perspective, if we know about them in advance and so can plan around them. In the case of donors who plan to give at least once per year, predictability is much more important from our perspective than frequency.↩
