Richard Seroter

Oh yeah, I forgot that we also made Audio input cheaper to $0.30/1M tokens so its even cheaper to use for use cases like speech transcription and audio time-stamping. developers.googleblog.com/en/gemini-25-f…

Seroter Daily Reading List – July 22, 2025 (#592): Today’s links look at doing architecture and product management in the AI era, what it looks like to more actively lead your team, and design principles for edge systems. seroter.com/2025/07/22/dai…

"Simplicity beats cleverness" and other good advice for junior devs in this video ... youtube.com/watch?v=p8ghbz…

Gemini 2.5 Flash-Lite, our fastest and most cost effective model, is now stable and ready for scaled production use!! It comes with native reasoning capabilities, a 1 million token context window, and is priced at ($0.10 in / 1M) and ($0.40 out / 1M).

"There, I found LLMs to be already useful, but during these 1.5 years, the progresses they made completely changed the game." antirez.com/news/154 < @antirez with an updated perspective on using AI coding tools, along with advice for using them correctly

"Our aim with OSS Rebuild is to empower the security community to deeply understand and control their supply chains by making package consumption as transparent as using a source repository." security.googleblog.com/2025/07/introd… < new project that already has ways to start using it

6 Design Principles for Edge Computing Systems thenewstack.io/6-design-princ… < real-life lessons from Michael and @BriChamb

Kudos to @chainguard_dev for basically inventing the market for secure base container images. @monkchips looks at this suddenly-active space with lots of players. redmonk.com/jgovernor/2025…

Gemini 2.5 Flash Lite now for production use! ⚡️🔦 It is the power horse, perfect high throughput uses cases! Available as `gemini-2.5-flash-lite`. - Free-Tier with 500 req/day then $0.1/$0.4 per 1M input/output token. - Supports controllable Thinking (can be turned off). -…

Gemini 2.5 Flash-Lite is now stable and generally available for developers and enterprise customers! ⚡ When designing a Gemini model, we think a lot about the tradeoffs between quality, cost, and latency. Previously with 2.0 Flash-Lite we optimized for cost-efficiency over…

Using AI to write a PRD marcabraham.com/2025/07/19/my-… < the input context matters a lot here, but AI can definitely help you communicate your thoughts in a more effective way

Are you supervising folks, or leading them? Both have a place, but they aren't the same thing. @Lethain has a good piece on moving from an "an orchestration-heavy to leadership-heavy management role." lethain.com/orchestration-…

Announcing Code Sandbox MCP, a simple code interpreter for your AI agents. Code Sandbox MCP is a simple, self-hosted code interpreter that gives AI agents like Gemini the ability to execute code in a local, containerized environment you fully control. How it works: 1. Starts a…

Can AI help software architects do their job? Sure. Maybe more than folks think. This article looks at a few areas of impact ... infoq.com/articles/archi…

What should we add next to Gemini CLI’s MCP support? 👇

Seroter Daily Reading List – July 21, 2025 (#591): Today’s links look at how LLM architectures differ, how to welcome vibe coders into tech communities, and what questions you should ask at a leadership offsite. seroter.com/2025/07/21/dai…

"We need to turn a solitary interaction with an AI into a shared journey with a community, and to move them towards learning the important lessons about engineering." lucumr.pocoo.org/2025/7/20/the-… < yes! @mitsuhiko has a wonderful post about opening the tent to a new crop of builders

New York, I am in you. Looking forward to a good week with teammates and customers.