Daily Brief
Slash Stack — October 2, 2026
A ranked daily snapshot of AI, software, systems, infrastructure, agents, blockchain, research, and tools from Discover.
Top story
Don’t be fooled—LLMs don’t reason
MIT Technology Review AI
On an afternoon in Seoul in March 2016, I watched a program I helped build put a stone on the fifth line of a Go board in what looked like a gift to its human opponent. Move 37 in game two of the five-game match looked so absurd that some commentators thought it was a…
What matters today
Dynamic workflows in Copilot CLI and the Copilot app
GitHub Changelog
Dynamic workflows are now available in Copilot CLI, the GitHub Copilot app, and the GitHub Copilot SDK. These let you define an orchestration in code to get the reliability and… The post Dynamic workflows in Copilot CLI and the Copilot app appeared first on The GitHub Blog .
Photon held a funeral for mobile apps. Now it has $4.5M to help replace them with agents.
TechCrunch AI
The startup helps developers build AI agents that work over iMessage, SMS/RCS, email, and other messaging platforms. It’s a bet that consumers will increasingly use agents instead of downloading apps.
Shopify debuts Canvas, a way to build online stores by chatting with AI
TechCrunch AI
Shopify’s new Canvas site builder lets merchants create and customize their online stores by chatting with its AI agent Sidekick, while watching the changes happen in real time.
The eternal complement
OpenAI
Advanced AI may matter most for the routine work behind breakthrough ideas. Explore why execution could shape the next economy and the pace of progress.
How Albertsons Companies is reimagining retail from the inside out
OpenAI
Albertsons Cos. is using ChatGPT Enterprise and the OpenAI API to help teams work faster and make grocery shopping easier for millions of customers.
Tools & releases
Show HN: I made a computer vision tool for evaluating deadlift form
Show HN · 5 pts · 1 comments
I’ve shared a few deadlift demos in the past. This new demo includes some new models, accessed through the VLM Run Gateway: - SAM 3.1 to segment the barbell weight plate - ViTPose+ Large to measure the hip hinge angle, which serves as a backup for segmenting the reps. The pose data can definitely be used more later. - Gemma 4 26B through the Gateway’s TypeSafe-compatible API to output the probability of the back being rounded or not. The predictions line up well with how I intentionally performed each rep. Of course, there are many caveats to what is good form, as it depends on the individual. All said, this has the pieces in place to quickly…
Show HN: The Kio Programming Language
Show HN · 5 pts · 0 comments
Kio is a statically typed, hosted language that is designed to be ultra-portable. Kio 0.1 supports eight host languages and more will be added in the coming weeks. Kio is based on polymorphic lambda calculus with higher-kinded types. Kio has type-driven macros (elaborators) and it can statically check asserted equivalences using a normalizer. Kio is a minimalistic language. It doesn’t have built-in effectful functions and it doesn’t even have built-in string or numeric types. Instead programs declare the capabilities they need and the host supplies them. The language is designed with AI, which is bound to raise some eyebrows, so I blogged…
Research worth reading
When Do Causal World Models Help Modular LLM Agents
arXiv cs.AI
arXiv:2610.00012v1 Announce Type: new Abstract: LLM agents increasingly act through modular systems, such as order, payment, inventory, and shipment services, where actions in one module change which transitions are valid in another. Standard world models usually fit observational traces, but this is not the quantity needed for intervention-time planning: a trace may show that payment precedes shipment without identifying whether payment authorizes shipment, inventory mediates the effect, or a hidden trigger explains both. We study this gap through FedCausalCompose, a causal world-model framework for modular LLM agents in which local actions…
K-Dense BYOK: An Open-Source AI Research Assistant That Runs Locally and Keeps a Hash-Chained Lab Notebook
arXiv cs.AI
arXiv:2610.00074v1 Announce Type: new Abstract: K-Dense BYOK (bring your own keys) is a free, open-source AI research assistant for scientists in any field that runs on the researcher’s own computer. The researcher supplies access to a model of their choice, hosted or running locally, and the application supplies everything else: a place for the work to run, a layer of scientific scaffolding, and a complete record. Each project is an ordinary folder, so the data, the code, the results, and the record stay on a machine the researcher administers and can be read years later without the application. Three things separate it from a chat assistant…
Context Language Models
arXiv · 153 pts · 41 comments
Articles
AutoSynthData: Generating Training Data for Enterprise Agents
Hugging Face
Uplifting conversion across the acquisition funnel with personalization using contextual bandits on AWS
AWS Machine Learning
Generative AI makes it cheap to produce personalized content at scale, but which variation do you show each customer? Amazon Payments used a multi-objective contextual bandit on Amazon SageMaker AI to personalize an acquisition funnel, achieving a high single-digit conversion lift for one audience, and learning why content, not the model, was the constraint.
Building ambient agents with Amazon Bedrock AgentCore: From event-driven signals to human-in-the-loop workflows
AWS Machine Learning
Ambient agents respond to events such as an Amazon S3 upload, a schedule, or an alert instead of waiting for a chat prompt. This post walks through building framework-agnostic ambient agents on Amazon Bedrock AgentCore using Amazon SQS, AWS Lambda, and Amazon DynamoDB, with a single ask_human tool and a Jobs page for human-in-the-loop review.
Hacker News signal
FTC is investigating OpenAI, Anthropic and other AI companies over product risks
Hacker News · 204 pts · 153 comments
Vote on which of Hacker News’ challenges for AI have been met
Hacker News · 169 pts · 193 comments
GPT-Synopsys: Frontier Intelligence to Revolutionize Chip Design
Hacker News · 181 pts · 109 comments
Figma restricts MCP access to whitelisted clients, excluding Pi
Hacker News · 182 pts · 102 comments
Ask HN: Who wants to be hired? (October 2026)
Hacker News · 114 pts · 378 comments
Share your information if you are looking for work. Please use this format: Location: Remote: Willing to relocate: Technologies: Résumé/CV: Email: Please only post if you are personally looking for work. Agencies, recruiters, job boards, and so on, are off topic here. Readers: please only email these addresses to discuss work opportunities. Searchers: try https://nthesis.ai/public/hn-wants-to-be-hired , https://www.wantstobehired.com .
This snapshot is generated automatically from the Discover ranking pipeline. It is a selection layer, not original reporting or AI-generated analysis.