Daily Brief
Slash Stack — October 16, 2026
A ranked daily snapshot of AI, software, systems, infrastructure, agents, blockchain, research, and tools from Discover.
Top story
ARIA: Runtime Inspection and Amendment for Multi-Agent Systems
arXiv cs.AI
arXiv:2610.20780v1 Announce Type: new Abstract: In LLM-based multi-agent systems (MAS), a local mistake can propagate as other agents build on it, turning a correctable error into a failed task. Diagnosing completed runs or repeatedly re-executing them to search for corrections does not provide a learned policy for intervening while execution is still in progress. We present Agent Runtime Inspection and Amendment (ARIA), a framework for learning when and how to repair ongoing multi-agent executions. Our key intuition is to turn execution-verified repairs into reusable supervision, moving repair search into data construction and training so…
What matters today
Multi-repo support and other improvements for GitHub Copilot in Slack and Microsoft Teams
GitHub Changelog
Multi-repo support in Slack and Microsoft Teams GitHub Copilot in Slack and Microsoft Teams now supports working across multiple repositories in a single conversation. Whether you’re tracking pull requests, investigating… The post Multi-repo support and other improvements for GitHub Copilot in Slack and Microsoft Teams appeared first on The GitHub Blog .
Upcoming deprecation of selected GitHub Copilot models in mid-November
GitHub Changelog
We will deprecate the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions) on November 16th, 2026: Model Deprecation date… The post Upcoming deprecation of selected GitHub Copilot models in mid-November appeared first on The GitHub Blog .
Amazon devices chief Panos Panay sees a future where AI devices replace the need to use apps
TechCrunch AI
Speaking at TechCrunch Disrupt, Amazon devices chief Panos Panay described a future where ambient AI devices work in the background, anticipating users’ needs instead of waiting for commands.
Meta launches an open-weight AI model that runs on Macs
TechCrunch AI
Meta and Apple have teamed up for the launch of the social media giant’s newest model, Muse Spark Open, which will run locally on Apple silicon.
Teaching students to think and learn through questions
OpenAI
Celebrate Teachers’ Day with AI for Educators in Brazilian Portuguese and see how Study Mode can help teachers support active, step-by-step learning.
Tools & releases
0.13.13: OpenAI browser tools and Cloud fixes
Browser Use
This release includes the OpenAI browser-tool driver and fixes two integration issues. Handle temporary empty Cloud tab URLs during navigation. Keep screenshots, crops, and pointer coordinates aligned on scaled displays. Provide 18 default browser tools and six optional actions through Browser Use Actor. Support local browsers, Browser Use Cloud, and borrowed browser sessions. Install the openai-tools extra with OpenAI Python 3.31+. OpenAI 3.x uses httpx2; use its DefaultAsyncHttpxClient for custom HTTP clients. Validation: all eleven driver tests pass. Both new regression tests fail on the earlier implementation. Pre-commit, type checks,…
langchain-core==1.6.11
LangChain
Changes since langchain-core==1.6.10 release(core): 1.6.11 ( #41260 ) feat(core): accept address inside LangChainTracer ( #41006 )
Show HN: BlastLoop, a structure-first coding method for AI agents
Show HN · 14 pts · 1 comments
Show HN: Dub Anything – Dub videos in each actor’s own voice
Show HN · 7 pts · 4 comments
There are many movies and shows out there with neither subtitles or dubs in English (or any other language). Pretty much impossible to watch. With SOTA AI now directing the process, you can do it locally on your machine. You basically just clone the repo, open up Codex or Claude and tell it to dub the video you want in the language you want. The repo contains all the scripts and guidance I’ve developed over the past few weeks to create dubs that are watchable, as an added bonus the voices in the dub are the actors own voices which is really nice. Also it’s self improving, each dub may modify the scripts for better fidelity. So feel free to…
Research worth reading
The World Won’t Wait: Evaluating and Teaching Agents Under a Live Clock
arXiv cs.AI
arXiv:2610.20665v1 Announce Type: new Abstract: Large language model (LLM) agents can solve complex interactive tasks, yet reasoning and tool calls take time. In continuously changing environments, an otherwise correct action may arrive too late. We introduce RealtimeBench, with 180 tasks across six game types, to evaluate agents while games continue running during inference. Paired evaluations show that GPT-6.1-sol outperforms the faster Jev when games are paused, but falls behind when they keep running. We propose Two-Timescale Offline Recursive Self-Improvement (TORSI): a slow teacher studies failures and tests corrections in paused games…
Evaluating Model Capabilities After Benchmark Saturation
arXiv cs.AI
arXiv:2610.20667v1 Announce Type: new Abstract: Rapid advances in AI capabilities are causing benchmarks to saturate. Once several models approach perfect scores, a benchmark loses its power to differentiate between them, and with it its utility for informing AI safety cases and frontier policies. Yet benchmark items produce far more information than the scores we typically extract from them: a full transcript of how each model solved the task. We investigate whether these transcripts can be used to assess model capabilities even after benchmark scores have saturated. We simulate saturation retrospectively using historical benchmark and model…
Accelerating the search for antimicrobial peptides with Google Antigravity
Google DeepMind
Accelerating the search for novel antimicrobial peptides using Google Antigravity for Science.
Articles
Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline
Hugging Face
Staying Evergreen: How we automated secure access and repo hygiene in a shared org
GitHub Engineering
Put native GitHub features to work to review outside collaborator access and archive stale repositories. The post Staying Evergreen: How we automated secure access and repo hygiene in a shared org appeared first on The GitHub Blog .
NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning
NVIDIA Technical Blog
Always-on agents are taking on longer, more complex enterprise workflows. A single request can involve reading a document, checking information across sources,…
Hacker News signal
Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta
Hugging Face · 766 pts · 389 comments
https://dev.meta.ai/resources/blog/build-with-muse-spark-ope… https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B https://9to5mac.com/2026/10/15/meta-launches-new-muse-spark-…
Neural networks are clean
already-clean.goodfire.com · 635 pts · 232 comments
https://twitter.com/nickcammarata/status/2110757819427574056
Simons Foundation launches $15M effort to help mathematicians navigate AI era
Hacker News · 237 pts · 192 comments
Using AI to reverse engineer hardware
Hacker News · 171 pts · 150 comments
Danish Supreme Court Finds That AI CSAM Is CSAM
Hacker News · 32 pts · 39 comments
This snapshot is generated automatically from the Discover ranking pipeline. It is a selection layer, not original reporting or AI-generated analysis.