Enjoyed watching "Explain How Kubernetes Works With GPU Like I’m 5" talk. The talk covers how you can setup a home k8s GPU lab. Video link: videocrawl.dev/studio?url=htt…

Videocrawl (videocrawl.dev) is LLM powered experience for videos. We use OpenAI models for our AI features. We upgraded from gpt-4o to gpt-4.1 and our transcript evals success rate has improved by 30%. Impressive work by OpenAI team.

Vercel AI SDK feels like the JavaScript equivalent of Python's LiteLLM.

I am finding gpt-4.1-mini better at instruction following compared to gpt-4.0. We are building a system that extract obligations from regulatory documents. gpt-4.1-mini is more accurate and complete compared to gpt-4.0

I am not liking Claude 4 models.

Just tried Gemini CLI with the Pro model — felt pretty dumb. Even after a detailed prompt with context, it kept asking, “tell me what you want to do.” Really disappointing. I use Claude Code daily it is so much better.

Hi Rahul Gandhi for the last 10 years, I’ve been telling my friends and colleagues that I truly believe — and hope — you will become the best Prime Minister India has ever had.

One of my favorite uses of Claude’s new create/edit files feature: generating synthetic PDFs. For one project, I generated 10 synthetic regulatory amendment PDFs (add/replace/delete) to thoroughly test document-processing agents. Great way to get unstuck and move forward.

Published a detailed post on building voice agent platform. We built on top of Pipecat. Post link: shekhargulati.com/2026/01/03/bui…