The risk of nuclear catastrophe is real, as is the fallout of the China–US domination game (hi there, spies). But no need to panic about Skynet.
Your observability UI shouldn't limit the questions you can ask. Explore how ClickHouse Observability Apps turns a prompt into custom investigation experiences, why SQL makes it possible, and what we still need to get right.
Article URL: https://stoppels.ch/2026/10/03/wake-me-up-when-ai-can.html Comments URL: https://news.ycombinator.com/item?id=50440657 Points: 26 # Comments: 7
Eval-driven development helps you build AI agents against a consistent set of metrics. Define good behavior, write the eval first, then compare experiments.
Article URL: https://zonderlabs.com/slop Comments URL: https://news.ycombinator.com/item?id=50433799 Points: 20 # Comments: 5
同样在非洲卖车，利润差了七倍。
arXiv:2611.08864v1 Announce Type: new Abstract: We present the Adaptive Scheduling Pipeline (ASP), an offline rollout scheduler for multi-instance asynchronous reinforcement learning (RL) of large language models (LLMs). ASP jointly reduces three sources of rollout underutilization - padding bubbles from intra-minibatch length heterogeneity, skewness bubbles from long-tail outputs, and sorting bubbles from fluctuations in training-queue occupancy induced by length-sorted dispatch - through a single offline preprocessing pass. This enables efficient multi-instance rollout that overcomes the early scaling plateau of single-instance inference while smoothing the arrival of generated samples at the trainer. We integrate the scheduler into an asynchronous architecture that decouples rollout from training while keeping policy lag observable and bounded. Complete ASP improves end-to-end throughput by up to 3.22 times and reduces iteration time by up to 76.8% relative to MindSpeed-RL, while reducing iteration time by up to 62.5% relative to verl. Within ASP, scheduling reduces mean iteration time by 10.9%. ASP also scales more robustly with additional generation resources than these baselines and shows no visible convergence degradation in the measured bounded-lag regime. ASP has since been used in an internal telecom-domain RL post-training workflow, reducing the reported training period from more than three months to about two months and producing a domain-enhanced model for knowledge answering and tool calling.
arXiv:2611.08640v1 Announce Type: new Abstract: Scaling test-time compute has proven highly effective at improving LLM reasoning. A popular method is best-of-n sampling, where a model generates many candidate solutions and one is selected. This motivates the question: how can we select the best candidate? When humans make choices, we find it more natural to compare two options than judge each in isolation. Additionally, when the options become complex, we like to judge the options one aspect at a time, such as comparing two job candidates on experience, communication, etc. In the test-time setting, candidate solutions should be judged in the same way. Here we introduce Aspect-wise Pairwise Tournaments (APT), which verifies by comparison and compares by aspect. Each matchup of a single elimination tournament is decided by a vote over multiple off-the-shelf aspect verifiers, each expressing a pairwise preference along its own aspect. Across five domains and three generator LLMs, APT improves over binary multi-aspect approval, self-consistency and reward model verification, with the largest gains on open-ended tasks. We find that both components matter; neither binary approval over the same aspects nor a generic pairwise judge at a matched budget matches APT. Because aspects are specified in natural language, APT also lets users steer selection toward properties they care about, better aligning with user preferences without needing to regenerate solutions. No component is trained, so APT transfers to new domains by simply rewriting prompts.
Claude Fable 5.2, designed for open-ended technical tasks, is now available on AI Gateway with improved coding, reasoning, and vision capabilities. It operates as an orchestrator or advisor, supports model fallbacks for cybersecurity classifier rejections, requires data retention (no Zero Data Retention), and can be accessed via the AI SDK, APIs, or integrated tools like Claude Code and Cursor. AI Gateway offers unified API access, cost tracking, failover options, and pricing transparency without markup.
Learn how OpenAI’s Control Room tracks model workloads across our research infrastructure and can rapidly stop them when safety or security concerns arise.
