arXiv:2610.32107v1 Announce Type: new Abstract: Participating in a conversation involves not only deciding what to say but also whether to speak at all. This judgment carries even greater significance in environments like the Werewolf game, where participants' interests conflict, because both utterances and silence are subject to interpretation and assessment by others. Therefore, determining when to speak, as well as what to say, is crucial for an LLM agent playing the Werewolf game. In this st
arXiv:2610.32109v1 Announce Type: new Abstract: Language models can answer a question from a supplied document or from their parametric knowledge. When later asked where the answer came from, what determines their source report? We study this by intervening on the model's key-value (KV) cache after the answer is generated and before the source question is asked. On a controlled factual task with four models (7B-32B), changing or removing the document's cache never changes the report. In contrast
arXiv:2610.32114v1 Announce Type: new Abstract: One approach to accelerating progress on AI alignment is to automate parts of alignment research itself. Doing so requires systems that can perform reliably on hard-to-supervise research tasks, including identifying flaws in research proposals and evaluating whether a proposed experiment supports its intended claim. To evaluate this capability, we introduce Tampered ML, a benchmark of 1,858 item-pairs, each consisting of an experiment proposal reco
arXiv:2610.32115v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) is a powerful paradigm for scaling Neural Machine Translation (NMT) and managing language heterogeneity. However, practical limitations hinder its deployment on resource-constrained devices: the entire expert pool must remain in memory, and the per-token compute budget is statically fixed during training by rigid top-k routing. We introduce EDWARD-NMT (Elastic Dimensions With Adaptive Routing and Dual-consistency for
Hi HN, we're Mike and Thom. Agents of the future should only have one tool (the interpreter, ideally a LISP eval), nothing more or less; to interact with the world. Agents remember by writing markdown files. NODECODE remembers by rewriting itself. And that is in itself a new paradigm in working with agents. What if memories, skills, MCPs, provider connectors, tools, etc. all live under the same image as *.lisp files instead of in disarray across random folders? Ask it for something it can’t do,
There are numerous apps on the market that promise to do just that, so we’ve compiled a list of some of the best ones to help you pick the right one for you.
平时都会跳出验证，这次没有跳出验证，直达某媒体网站，似乎是伦媒。刷新一下，还是错误页面，但链接仍然是 V2EX 的。网址也没填错啊，从浏览器收藏那里打开的。看了一下与此同时，好多其他网站打不开 比如 google 等。怀疑是网络问题，换别家的，正常了。是 V 站被攻击了还是网络工具的问题啊，有没有人大清早遇到的
事情经过： 不知道什么时候开始，我的邮箱不断收到 Apple 账户的购买收据，购买行为不是我本人操作的。 我没有创建过这个 Apple 账户，也没有授权别人使用我的邮箱。目前自己的银行卡、信用卡等没有发生实际扣款，但一直收到陌生人的购买邮件。 我尝试用自己的邮箱登录，结果系统要求回答安全提示问题。但我根本不知道答案，无法继续登录或重置。 我联系了 Apple 官方支持。在线聊天后，对方安排同事电话联系我。电话沟通后，客服表示无法直接封锁这个账户，也无法帮我取回账户，必须由我自己登录并回答安全提示问题，才能重置账户。 问题就在这里： 邮箱明明是我自己的，但别人用它注册了 Apple 账户，我却因为不知道对方设置的安全提示问题而无法处理。 我理解 Apple 需要保护账户安全，不能随便把账户交给别人。但现在的情况是，我并不是要取回对方的账户，也不是要查看对方的个人资料，我只是希望 Apple 核实邮箱归属，并解除这个邮箱与陌生账户的关联，或者至少阻止继续向我发送这些购买收据。 结果客服给出的方案相当于让我自己解决一个根本无法通过正常流程解决的问题。 有没有遇到过类似情况？ 我通过邮箱重置密
I keep missing my AI agents' requests for my attention. So I had it build a thing that glitches the whole screen, like the glitches in the SpiderVerse movies.