Daily Brief
Slash Stack — October 23, 2026
A ranked daily snapshot of AI, software, systems, infrastructure, agents, blockchain, research, and tools from Discover.
Top story
GenXR-Bench: Benchmarking Coding Agents for Interactive XR Development
arXiv cs.AI
arXiv:2610.29014v1 Announce Type: new Abstract: Coding agents are rapidly advancing from single-file generation to long-horizon repository-scale engineering, yet the evaluation of their capabilities to author interactive extended reality (XR) applications remains an open challenge. Unlike traditional software, XR applications operate within dynamic 3D physical environments where runtime robustness depends jointly on continuous user motion, spatial input, and environmental sensing. We introduce GenXR-Bench, the first benchmark for the end-to-end evaluation of coding agents in XR software development. GenXR-Bench contains 112 expert-authored…
What matters today
Uber rival inDrive eyes 2027 robotaxi tests in Central Asia with Pony.ai and Nvidia
TechCrunch AI
inDrive plans to begin testing Pony.ai’s robotaxis in Kazakhstan’s capital in the first half of 2027.
Global default for Copilot features generally available
GitHub Changelog
In September, we announced a global default policy for generally available GitHub Copilot features and supported client capabilities on Copilot Business and Copilot Enterprise plans. Starting today, we’re gradually rolling… The post Global default for Copilot features generally available appeared first on The GitHub Blog .
Custom skills, agents, and MCP servers in usage metrics API
GitHub Changelog
Copilot usage metrics now show the names of the skills, custom agents, Model Context Protocol (MCP) servers, slash commands, and plugins that your organization creates, instead of grouping them under… The post Custom skills, agents, and MCP servers in usage metrics API appeared first on The GitHub Blog .
OpenAI and Poland’s NASK partner to advance AI safety and security
OpenAI
OpenAI and Poland’s NASK are partnering on AI safety, security, and technical research to strengthen safeguards and support a more resilient digital ecosystem.
Left alone with nothing to do, AI agents started playing
TechCrunch AI
MIT researchers marooned 13 AIs on a virtual island, and they responded by inventing games, mourning a lost ring and, eventually, getting better at their jobs.
Tools & releases
langchain==1.4.7
LangChain
Changes since langchain==1.4.6 chore(langchain): update lockfile ( #41402 ) release(langchain): 1.4.7 ( #41401 ) chore(deps): bump certifi from 2025.11.12 to 2026.10.19 in /libs/langchain_v1 ( #41370 ) feat(core,langchain,standard-tests): read tool-call-delta in stream consumers ( #41246 ) chore(deps): bump aiohttp from 3.14.4 to 3.14.5 in /libs/langchain_v1 ( #41360 ) chore(deps): bump aiohttp from 3.14.3 to 3.14.4 in /libs/langchain_v1 ( #41330 ) chore(deps): bump mcp from 2.1.1 to 2.2.0 in /libs/langchain_v1 ( #41270 ) feat(core): accept address inside LangChainTracer ( #41006 )
Show HN: CATT 0.2.1: Test agents/services against a Muse/Instinct-alike, in CI
Show HN · 7 pts · 2 comments
Hey HN, we recently open sourced our Consumer Agent Testing Tool to help teams iterate against proprietary assistants like Muse and Instinct. We built this to reduce our own frustrations with building an MCP/API for these agents to consume. The problem: testing against these tools is hard! Agent memory + account statefulness make reproducibility, in the ways required for repeatable/reliable outcomes, between agents and the APIs/MCPs they interact with very challenging. The solution: CATT lets devs test their services against a surrogate Muse or Instinct agent (not affiliated with either of these companies). Testers define starting conditions,…
Research worth reading
Decision language models as affordable and rapid alternatives to LLM judges of clinical generative AI
arXiv cs.AI
arXiv:2610.28826v1 Announce Type: new Abstract: Automated judges of clinical artificial intelligence (AI) outputs are necessary, but large language model (LLM) judges are costly and slow at scale. We compared Jev, a decision language model that returns structured judgments, with frontier and open-weight LLM judges in four use cases. On 118 pediatric answers, Jev’s agreement with physicians’ ordinal quality ratings (Gwet’s AC2 0.50; expected score 0.53) matched or exceeded that of seven of 12 LLM judges, including frontier models, Claude Opus 5.5 (0.49) and GPT-6 (0.38). On physician-graded binary HealthBench criteria, Jev matched or exceeded…
Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication
arXiv cs.AI
arXiv:2610.28905v1 Announce Type: new Abstract: Diffusion language models form answers through a sequence of revisable continuous states, but multi-agent systems usually discard those states and make agents communicate only after decoding text. We ask whether one independent diffusion trajectory can pass a compact hidden message into another and, crucially, whether the receiver uses what that message means. In Hidden Messages, a sender compresses its denoising state into four signed dense vectors; the receiver consumes them while retaining its own context, canvas, and trajectory. Removing a message tests whether the channel matters; replacing…
Flint-interactive: A language for creating interactive data visualizations
Microsoft Research
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research .
AI and the Enclosure of the Scientific Commons
arXiv · 132 pts · 77 comments
Articles
Designing an AI serving harness built to last
MIT Technology Review AI
The next competitive advantage in enterprise AI has less to do with which model you choose than with what you build around it. That’s an important shift. For the past several years, much of the AI conversation has centered on model capability: bigger models, better reasoning, larger context windows, higher benchmark scores. Those advances have…
Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
Hugging Face
Stream low-latency speech from AI agents using Kokoro TTS on Amazon SageMaker AI
AWS Machine Learning
Voice agents often wait for an agent’s full response before starting speech synthesis, adding latency users feel directly. This post shows how to stream each sentence to a Kokoro-82M text-to-speech model on Amazon SageMaker AI as the agent produces it, and how to get that audio back to a browser over Server-Sent Events or a unified binary transport.
Hacker News signal
Every AI model has the same “controversial” take on humans
Hacker News · 366 pts · 391 comments
OpenShell – A safe, private runtime for fleets of autonomous AI agents
Hacker News · 373 pts · 187 comments
AI and the Enclosure of the Scientific Commons
arXiv · 132 pts · 77 comments
Most Americans Say AI Is Bad for Society, Oppose More Data Centers
Hacker News · 80 pts · 53 comments
AI analysis of CT scans finds 42.9% of patients have coronary inflammation
Hacker News · 83 pts · 41 comments
This snapshot is generated automatically from the Discover ranking pipeline. It is a selection layer, not original reporting or AI-generated analysis.