When LLM Batch Processing is Faster than Synchronous

When LLM Batch Processing is Faster than Synchronous

A project I am working on for JM Addington Technology Solutions and CyberSecureRIA involves summarizing > 500,000 emails and documents with an LLM. That’s a lot! There will be ongoing work, but the first 500,000 are a bulk process. To save money, I used...
Give Claude Code Access to Gemini

Give Claude Code Access to Gemini

One of the best things I’ve done recently is to install Simon Willison’s llm tool in my development environments and give Claude Code instructions on how to use it. I set the model to gemini-2.5-pro-preview-05-06 by default, but I plan to try the latest...
OpenAI Adopts MCP

OpenAI Adopts MCP

My notes to my peer group on the adoption of MCP by OpenAI: https://threadreaderapp.com/thread/1904957755829481737.html?utm_source=tldrnewsletter MCP 🀝 OpenAI Agents SDK You can now connect your Model Context Protocol servers to Agents: We’re also working on MCP...
AI Coding

AI Coding

A friend asks: How do you handle long back and forth threads with your AI code monkey du jour? And how does AI code monkey handle them? Does it start losing context, getting weird? You said you mostly use APIs β€” with what UI? I have questions. πŸ‘€ Long threads: I move...
OpenAPI Spec for Kaseya’s IT Glue

OpenAPI Spec for Kaseya’s IT Glue

Kaseya has decent documentation on their IT Glue API, but does not publish it in a standard format (Swagger / OpenAPI). To fix that deficiency, I wrote a script that parses the official page and create an OpenAPI 3.0 compliant spec from it, find the script and the IT...