Nadeesha Cabral

“Here’s today’s batch,” he said gleefully, handing over a double-bagged parcel of half-brewed slop weighing exactly two pull requests and 11,700 lines of code.

Heard the news?

This is a companion piece explaining the worldbuilding behind “The Relentless Gardner” from A Consensus in Time.

For the longest time, I’ve thought MCP is a weird protocol.

The book I unashamedly recommend to anyone in the “self-help” category is Atomic Habits [1].

Joe, I am writing this in words.

It is a perfect summer afternoon.

I had a name once.

Taleb once said that it’s easy to take the risks you can measure rather than measure the risks you can take.

I’m coming to the realisation that there’s a widely applicable heuristic to figure out who’s grifting over-promising in the race to build “AI-native” products.

The reason why LLMs are programmatically useful is because they can produce structured outputs.

Dev Tools are the hardest business on earth.

Most of the complex systems (humans, computers, pirate ships) that didn’t break apart, seems to have ascended a point where things got “bad before it got better”.

Cathedral and the Bazaar is something I use often to see which side of an argument I want to be on.

Originally published at Inferable Blog ULIDs are awesome.

Originally published at Inferable Blog OpenAI, Anthropic, and others have built specialized APIs for tool calling.

Originally published at Inferable Blog Like many teams building real-time systems with Node.js and TypeScript, we’ve been exploring ways to handle real-time updates at scale.

Originally published at Inferable Blog When building distributed systems that need to process jobs or tasks concurrently, one of the most challenging problems is ensuring that work is distributed efficiently without duplication.

Originally published at Inferable Blog Temperature is one of the most important settings when working with Large Language Models (LLMs).