sgnt.ai

I used to write little translators for my bank exports.

I hit enter too early on a message to Claude and it identified the fundamental design flaw in our codebase before I could describe it.

I posted my AI agent jail to Show HN.

We need a better vocabulary for describing contribution in the age of generative AI.

Over and over again, despite the best efforts of humans, the most effective AI systems come down to one simple idea: finding the right shaped line that fits some data points.

Existing articles often focus on a chunk as a singular concept: you split the article into paragraphs, say, and use these to feed the LLM, generate embeddings, and quote back to the user.

You delivered your vision quickly using one of the many excellent LLM-based coding tools, users are happy.

Embeddings are a core AI concept that underpin a great deal of what we today think of as being AI.

In our application, the chatbot can’t hide behind a loading spinner; users keep talking and expect it to pivot instantly.

While working on LLM-driven NPCs, I observed significant improvements in several areas by adding a simple component: in-memory free-text search

Don’t let an LLM make decisions or implement business logic: they suck at that.

If your team promises to deliver (or buy!)

or, reducing hallucination and making in-generation adjustments to LLM responses