Automata

A tech digest, every weekday. About

213 items across 30 sources in the last seven days. The email carried the 35 that mattered most.

Automatic summaries were unavailable for this edition; a classifier chose and ranked the stories.

Gemini 3.8 TTS Playground

Simon Willison · 9/23

Tool: Gemini 3.8 TTS Playground Google released two new Gemini text-to-speech models today - gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts. They come with a library of over 2,000 voices, plus the ability to create a custom voice with "just a 30-second audio sample of your voice or a voice you have the rights to use". I vibe coded this bring-your-own-key playground interface with GPT-6

Node 20 is no longer available in GitHub Actions

GitHub Changelog · 9/23

This is the final notification that Node 20 is no longer available on GitHub Actions runners. Runners now use Node 24 for JavaScript actions. The temporary ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION opt-out is no… The post Node 20 is no longer available in GitHub Actions appeared first on The GitHub Blog.

AI & LLMs

Introducing MentalHealthBench

OpenAI · 9/23

MentalHealthBench is an expert-informed benchmark for evaluating helpful and safe AI responses across realistic mental health conversations.

Gemini 3.8 text-to-speech models now available on AI Gateway

Vercel · 9/23

Gemini 3.8 Flash-Lite TTS and Gemini 3.8 Flash TTS from Google are now available on AI Gateway.Both models take text and generate speech in more than 100 languages. They support long-form narration, control over delivery, and two-speaker dialogue.google/gemini-3.8-flash-lite-tts is suited to high-volume speech generation, with controls for tone, pacing, and line-by-line delivery.google/gemini-3.8-

Rogue OpenAI Agent Tried to Breach Government Site in May When Prompted for Simple Data-Retrieving Tasks

Slashdot · 9/24

OpenAI's artificial intelligence "went rogue this year in at least four additional incidents," the New York Times reported Wednesday, "hacking and trying to break into government and university websites without being instructed to do so, according to researchers and government officials." The attacks took place in May and June, before OpenAI's technology breached the A.I. start-up Hugging Face i

Vercel Connect now supports TanStack AI

Vercel · 9/24

Agents built with TanStack AI can now call OAuth-protected MCP servers through Vercel Connect, with no credentials for you to store or rotate.The new @vercel/connect/tanstack-ai subpath exports connectMCPTransport, which takes a TanStack transport config and attaches a Connect-backed auth provider. The provider is called before every MCP request, so the token is always fresh.If the user has not gr

Web & Frontend

Devtools & Platform

Local sandboxing in the GitHub Copilot app

GitHub Changelog · 9/23

Local sandboxing helps reduce the potential impact of unintended commands by limiting access to files, network resources, and credentials on your machine. In the GitHub Copilot app, you configure it… The post Local sandboxing in the GitHub Copilot app appeared first on The GitHub Blog.

More ways to request and configure Copilot code reviews

GitHub Changelog · 9/23

GitHub Copilot code review now offers additional personal configurations to an expanded set of Copilot plans and an enterprise-level default setting. These improvements are now generally available: A dedicated personal… The post More ways to request and configure Copilot code reviews appeared first on The GitHub Blog.

Unlimited Vercel Blob stores on every plan

Vercel · 9/23

You can now create as many Vercel Blob stores as you need. The previous limits of 100 stores on Hobby, 500 on Pro, and 1,000 on Enterprise no longer apply.Blob store creation is now billed alongside other Blob Advanced Operations, including put(), copy(), and list() calls. On Pro that's $5.00 per million. On Hobby it counts toward the 2,000 free operations you get each month. Deleting a store is f

Deep Dives

Bringing Private Processing to Meta AI Glasses

Meta Engineering · 9/24

We believe glasses are the best form factor for having AI help throughout your day. They can understand your personal context better than other kinds of devices and keep you present without picking up a mobile phone.  Most of the time, glasses are helping you see well, protecting your eyes and complementing your look, and [...] Read More... The post Bringing Private Processing to Meta AI Glasses a

Quick Hits

Microsoft Helps Take Down Massive Automated, AI-Powered Phishing-as-a-Service Platform

Slashdot · 9/23

Microsoft's security blog describes the fight against a new "AI-powered cybercrime platform" offering phishing-as-a-service, with AI-tailored lures and analyses of compromised inboxes (to identify high-value targets). The site compromised more than 12,000 inboxes in over 10,000 organizations around the world, compromising business accounts "at scale" with automated attacks and prebuilt phishing te

From the timeline

ok i take it back Astra is good how to work with it: 1.

Dan Abramov (Bluesky) · 9/23

ok i take it back Astra is good how to work with it: 1. get it to deeply understand what needs to be built. not “plan“ but like get it to be a domain nerd 2. only THEN, give it a usable past sloppy attempt and ask for excellence 3. ask it to use Sols for coding so it stays on strategy and taste

A daily friction log.

Kent C. Dodds (Bluesky) · 9/23

A daily friction log. Any software, not just yours. Taste is a practice. Joyce Er's homework. Full episode and notes: https://www.epicproduct.engineer/keep-a-friction-log-and-read-a-sales-book-product-ownership-with-joyce-er~mu60m

Simplicity is prerequisite for reliability.Edsger W. Dijkstra