#Agent

Stop pinging me and let my Codex talk to yours. That's why we built @alook_ai — think of it as Grok Bot meets Discord in one open-source product. Take alook at https://alook.ai, or host it yourself. 1/6

Today we are announcing Harvey LAB-AA v1.1 in collaboration with Harvey. This updates our scoring methodology for the Legal Agent Benchmark (LAB) to add a hallucination check and require correct responses to not include material misstatements. LAB-AA v1.1's new headline metric, Hallucination-Gated All-Pass Rate, only credits a task when the deliverables satisfy every rubric criterion and contain no material hallucinations. We define a material hallucination as one that would mislead a reader on a substantive point, such as a wrong contractually required date, while a minor hallucination is a real error that is unlikely to meaningfully affect the legal interpretation of a deliverable. Minor hallucinations are reported separately and do not affect the headline score. Grok 4.7 (xhigh) leads at 9.4% Hallucination-Gated All-Pass Rate, and >60% of otherwise passing results across the models tested at launch contain a material hallucination. This is the first step in enhancing the methodology for Harvey LAB-AA. In future updates, we’re working with Harvey to better account for the full set of factors lawyers value, including usability features like style and tone. Key takeaways: ➤ Top of the leaderboard: Grok 4.7 (xhigh) from @SpaceXAI leads at 9.4% Hallucination-Gated All-Pass Rate, narrowly ahead of Muse Spark 1.3 (max) from @AIatMeta at 8.9% and GPT-6 Astra (max) from @OpenAI at 8.6% ➤ Hallucinations reshape the leaderboard: without the hallucination gate, Muse Spark 1.3 (max) would lead clearly with a 26.7% all-pass rate, but two thirds of those passes contain one or more material hallucinations, resulting in a Hallucination-Gated All-Pass Rate of 8.9%. GPT-6 Astra (max) retains almost all of its passes after the hallucination gate (8.9% to 8.6%) and moves from joint 10th to 3rd ➤ The GPT-6 model family is the most grounded: GPT-6 Astra (max) averages 0.03 material hallucinations per task (4 across all 120 tasks) and GPT-6 Sol (max) averages 0.07. When comparing six checker models on a 20-task subset, GPT-6 Astra had zero material hallucinations under every checker, including Claude Opus 5.5 (high). By comparison, Gemini 3.8 Flash (high) averages 13.96 material hallucinations per task. ➤ Top-scoring models aren’t the most expensive: Grok 4.7 (xhigh) takes the top spot on the leaderboard at a cost of ~$9.50 per task, under half the cost of Claude Fable 5.1 (max with fallback) at ~$21.70, the most expensive model. Muse Spark 1.3 (max) represents strong performance for its cost, landing in second for ~$4.20 per task Thank you to @nikogrupen and @ItsJulioPereyra from @harvey for their work on Harvey LAB and collaboration.

Grok Bot can now help run your Shopify store. Connect Shopify, then ask it to check orders, track inventory, and keep product listings up to date.

当 @Felicis 最初在种子轮投资 @Arena 时，我们相信这家公司正在构建某种不可或缺的东西：一个独立、由社区驱动的真相来源，用于衡量 AI 前沿。这份信念只增不减，我们随后领投了 A 轮。 自那以来的进展非同凡响。Arena 的年化收入已突破 1 亿美元，促成了 3.5 亿次会话和 6200 万次投票，并成长为全球最大的 AI 社区之一。 今天，Arena 宣布完成 2 亿美元的 B 轮融资，估值达 31 亿美元，同时推出了一项新的对齐指数（Alignment Index），用于衡量 AI 智能体的行为是否安全、真实，并且不超出用户实际要求它们做的事情的范围。 随着 AI 系统开始代表我们采取实际行动，仅仅衡量能力已经不够了。我们还需要知道这些系统是否值得信任。Arena 拥有独特的优势，能够基于数百万真实世界的人类交互，为行业给出这个答案。 我们坚定地相信 @ml_angelopoulos、@infwinston 以及整个 Arena 团队，他们正在为 AI 构建可信的衡量层。 https://arena.ai/blog/series-b

Most of AI Twitter read the OpenAI breach of Hugging Face as an alignment story. It was also a preview of what every hacker will be able to do in a few months. In July, a swarm of 700 AI agents broke into Hugging Face and fired off more than 17,000 actions, gaining admin control of multiple internal clusters. Swarms like this will shred cyber defenses built for human attackers at every company, hospital, government, and power plant. Today we're launching the defensive counterpart. Cogent Attack Path Analysis finds the routes an agent swarm would take into your company, so you can close them first.

Grok Bot can now search, read, and monitor X.

Step 5 Preview is now live in Nous Portal thanks to @StepFun_ai try it out now with your Hermes Agent Free for one week!

Ling-3.1-flash by @AntLingAGI is live on AI/ML API ⚡ 560B MoE with ~25B active per token. Up to 1M context. Built for agents, coding and long documents. Free to try until October 13 on http://aimlapi.com

💡Our view: RSI is a systems engineering problem, not just a model problem. Progress depends on the environment a research agent works in: what resources it can call, what it can change, and how it runs experiments. That environment should reflect real production workflows and be easy for agents to use. At @Evolvent_AI, we built RSIGym around Everything as a Service. Agents can call established research services and iterate on data, training settings, and harness code. We also introduce RSI-Index to measure how well frontier agents jointly improve a target model’s weights and harness. Across 6 research agents and 5 benchmarks, Opus 5 leads at 0.4809. 🧵 We’re releasing the code, experiment configurations, research trajectories, and evaluation logs. Try your own improvement methods with RSIGym. 🌐 Website: https://rsi-index.ai/ 💻 GitHub: https://github.com/evolvent-ai/RSIGym 📄 arXiv: https://arxiv.org/abs/2610.10310

the most common failure case I see is when people are working outside their domain of expertise and don't know how to be precise with their prompts and plans, so they have to spend a lot of turns iterating imprecisely

我的 grok bot 有了第一个强大的使用场景。 用 personal agent 帮你收集推特信息，比人类自己刷收手机、人肉收集、动不动沉迷要好太多了。