The daily ledger

Note on 24th September 2026

The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder. We can do amazing things with them, but unlocking their full potential requires extraordinary…

A Developer’s Guide to Gemini 3.5 Transcribe

Code tutorial → https://g.dev/cloud/gemini-3-5-transcribe-github Code script → https://g.dev/cloud/gemini-3-5-transcribe-live-github Docs → https://g.dev/cloud/3-5-transcribe-docs Explore how to build speech-to-text…

commit-rewriter 0.2

Release: commit-rewriter 0.2 Support for branches other than the default branch. Use uvx commit-rewriter --branch other to run against another branch. #3 Tags: git

Automating coherent long-form video generation

Generative AI

datasette 1.0a41

Release: datasette 1.0a41 Alec Garcia added support for OpenTelemetry to Datasette in this release. I've also refactored all of Datasette's modal dialogs to a single Web Component, which is now documented for other…

Turn Audio into Action with Gemini 3.5 Transcribe

Blog → https://g.dev/cloud/gemini-3-5-transcribe Docs → https://g.dev/cloud/3-5-transcribe-docs Code tutorial → https://g.dev/cloud/gemini-3-5-transcribe-github This video explores how to transform your enterprise audio…

Prevent surprise cloud bills: enforce hard spending caps on Gemini API & Vertex AI

Calling AI APIs and LLMs can burn through your cloud budget faster than traditional workloads. Standard budget alerts warn you after you've already racked up costs, but they don't actually stop the traffic. In this…

Accelerating vision-language models with LFM2.5-VL-DSpark

Gemini is coming to your city

Build with Gemini is a worldwide event series bringing hands-on AI development to cities around the globe. With tracks for business leaders, architects, and app developers, attendees can move beyond presentations and…

Amazon SageMaker HyperPod Inference Gateway for scalable LLM inference

Amazon SageMaker HyperPod Inference Gateway is a Kubernetes-native, GPU-aware routing system that deploys as a single EKS managed add-on on existing SageMaker HyperPod infrastructure with zero application changes. By…

Google Gemini can present cartoon or lifelike avatars to lip-sync generative chatter

Despite uncertainty about how human mimicry affects people, DeepMind fakes are here

AI Agents Are Now Operating Enterprise Networks. Trust Sets the Limits.

AI agents already act in production networks at 51% of surveyed organizations. Cisco and Omdia’s research explores how far companies will extend that authority and which controls they expect.

Evolving Argo Workflows for AI: New Features, Tuning, and Multi-Tenant... Shuangkun Tian & Yashi Su

Don't miss out! Join us at our next KubeCon + CloudNativeCon event in Salt Lake City, United States (Nov 9–12, 2026). Connect with our current graduated, incubating, and sandbox projects as the community gathers to…

From Containers To Agents: The Next Cloud Native - Di Xu, Xiaohongshu

Don't miss out! Join us at our next KubeCon + CloudNativeCon event in Salt Lake City, United States (Nov 9–12, 2026). Connect with our current graduated, incubating, and sandbox projects as the community gathers to…

Beyond Model Sharding: Atomic Scheduling and Disaggregated LLM Serving... Kay Yan & Chen Zicong

Don't miss out! Join us at our next KubeCon + CloudNativeCon event in Salt Lake City, United States (Nov 9–12, 2026). Connect with our current graduated, incubating, and sandbox projects as the community gathers to…

PD Disaggregation VLLM Deployment on Alternative AI Accelerators Using Llm-d - 纪飞 王 & Mengxuan Li

Don't miss out! Join us at our next KubeCon + CloudNativeCon event in Salt Lake City, United States (Nov 9–12, 2026). Connect with our current graduated, incubating, and sandbox projects as the community gathers to…

Project Lightning Talk: Run Sandbox Securely and Cost-Effectively with OpenKruise... Zhang Zhen

Don't miss out! Join us at our next KubeCon + CloudNativeCon event in Salt Lake City, United States (Nov 9–12, 2026). Connect with our current graduated, incubating, and sandbox projects as the community gathers to…

Claude Opus 5.5 Broke Our GPT-6 Benchmark

We tried to benchmark Claude Opus 5.5 against GPT-6 Sol. Then Opus kept building, judging, fixing, and iterating until the benchmark itself stopped making sense.

Meta’s Big AI Bet Now Fits on Your Keychain

Meta Connect put Muse on a keychain, promised it for AI glasses, and gave its personal agent voice, email, and computer-use ambitions. Here’s why I’m excited.

The Dark Side of Jev: 83% Confidence, 19% Accuracy!

Why developers are ditching traditional LLMs for typed decisions, and why Jev's confidence scores need a serious second look.