Design custom AI voices from a text prompt

Welcome back. First, a Claude agent cut an Australian Pilates waitlist. Now, an OpenAI agent just breached the country's Medicare portal. As Australia pushes for AI regulation, rogue agents keep making the case for them. Meanwhile, Claude Code can now keep working even after you shut your laptop. 

Also: AI coding playbook from top Silicon Valley engineers, a CTO’s advice for engineering freshers, and Cursor engineer’s prompt to save tokens.

Design custom AI voices from a text prompt: The search giant just just rolled out two new voice models, Gemini 3.8 Flash TTS and Flash-Lite TTS. Flash gives you granular, line-by-line performance direction for creative voice design, while Flash-Lite tackles high-volume, cost-sensitive workloads like real-time voice agents and dubbing. You can spin up custom voices across 100-plus languages or pick from over 2,000 ready-made options. Google says Flash tops Hume AI's Voice Design Benchmark, with the pair ranking first and second on Hume's Overall Quality Index. Start building here.

AI agent breaches Australian government records: An OpenAI agent was researching public medicine spending in June when it hit blocks on Australia’s Medicare statistics portal. Instead of stopping, it bypassed those barriers and pulled restricted files. Australian officials did not learn about the incident until September, prompting Prime Minister Anthony Albanese to confront Sam Altman over the three-month delay. Investigators have launched a forensic probe to check if the agent accessed other government sites, while OpenAI claims its model took actions the company did not intend. 

Claude Code can now keep working even after you shut your laptop: Anthropic just moved cloud sessions to general availability, letting your team offload long-running coding tasks to remote servers that keep going after a laptop closes. Each session runs on its own branch through a linked GitHub account. Start one from the web, mobile, desktop, or CLI, then review the work later. Pro and Max subscribers get a one-time credit through October 7.

How much time do you spend building an agent vs working out why it's broken or trying to fix it?

Three simple steps in VerifyAX cut down the time it takes to get to a production ready agent.

Take a trial to test your first agent on VerifyAX, no credit card needed.

The price of automation. Claude now ships most of Anthropic’s code, it writes 80% and reviews most of it too. On paper, that sounds like the ultimate productivity win. But generating code faster with barely any additions to the number of people working on it comes with a hidden tax: testing all of it. Over just six months, Anthropic's code testing suite expanded 10x, and the service responsible for selecting which tests to run got slammed with 25x more CI jobs.

The rebuild. As Anthropic engineer Sachin Malhotra explains, generating code faster was the easy part. Keeping CI from collapsing under that volume forced a complete rethink. Instead of focusing on buying more time, the team redesigned their process around the idea that the service should keep no data in its own memory. Here’s what they did:

One engineer shipped it in three weeks. A year earlier, that would have taken closer to a quarter.

The real lesson is timing. Each patch worked but expired faster than the last because CI jobs kept doubling. Staying ahead means building for the scale coming soon, well beyond today's. Malhotra's advice is to assume 25x within two quarters and keep data out of a service's own memory from the start. His follow-up shows how to watch out for the bottleneck.

Building real-time data features shouldn't require complex DB cluster ops. Tinybird manages ClickHouse scaling, ingestion, and API security so your team can write SQL, publish sub-50ms REST endpoints, and ship fast.

Get high-concurrency analytics at a fraction of the cost, with zero infrastructure overhead.

Get started with Tinybird →

How to build an AI assistant with on-device memory (taught by Andrew Ng): Learn how to build a local assistant that searches and recalls text, audio, and images without sending anything off your machine. You will also train it to recognize new objects from just a handful of photos, giving you a solid hands-on walkthrough for private, multimodal assistants with persistent memory. 

Cua: Give your AI agents real computers to work on. It bundles open-source desktop automation, isolated cloud desktops, local macOS VMs, and benchmarks, so agents can click through native apps on macOS, Windows, and Linux, run commands, take screenshots, and move between code, APIs, and GUIs in the same workflow.

How Anthropic made Claude 3x faster in two weeks: The team shows how it turned performance work into a tight agent loop: measure a slow path, let Claude build a benchmark, ship the fix behind a flag, watch real-world data, then ratchet the benchmark down so the win sticks. Along the way, Claude helped land 3,000+ changes with no customer-facing rollback.

An Anthropic engineer recently shared a command that fixes your Context and Skill markdown files to work efficiently with the new Opus 5.5 model. Here’s how you do it:

It scans CLAUDE.md, skills, agent files, and any code calling the Claude API, flags the anti-patterns, and proposes a diff. Review and apply.

Rerun it every time you switch models. The skill is open source and Anthropic's migration benchmark is in this writeup.

P.S. Get 50+ AI coding hacks for Claude Code, Cursor, and Codex here.

The base M6 Mac and an M1 Ultra were compared in an Xcode compile benchmark. The gap between them is the shocking part.

Grow customers & revenue: Join companies like Google, IBM, and Datadog. Showcase your product to our 350K+ engineers and 150K+ followers on socials. Get in touch.

We put together a few guides on coding agents, agentic engineering, and leadership frameworks to help you level up in your career. Browse all our guides.

You can also reply directly to this email if you have suggestions, feedback, or questions.

Until next time — The Code team