Submissions from sgnt.ai

		Understanding Modern AI Is Understanding Embeddings: A Guide for Non-Programmers (sgnt.ai)
		3 points by dekervin 22 days ago \| past
		RAG chunking isn't one problem, it's three (sgnt.ai)
		4 points by petesergeant 7 months ago \| past
		I will fix your vibe-coded MVP – sgnt.ai (sgnt.ai)
		19 points by yeahyeah321 7 months ago \| past \| 3 comments
		Understanding Modern AI Is Understanding Embeddings: A Guide with Lots of Dogs (sgnt.ai)
		1 point by petesergeant 9 months ago \| past
		Understanding modern AI is understanding embeddings: a guide with almost no math (sgnt.ai)
		3 points by petesergeant 9 months ago \| past
		When Users Won't Wait: Engineering Killable LLM Responses (sgnt.ai)
		4 points by petesergeant 9 months ago \| past
		In-memory free-text search is a super-power for LLMs (sgnt.ai)
		3 points by petesergeant 9 months ago \| past
		Don’t let an LLM make decisions or execute business logic (sgnt.ai)
		325 points by petesergeant 10 months ago \| past \| 169 comments
		Four bad definitions of "Agentic AI" (sgnt.ai)
		2 points by petesergeant 10 months ago \| past
		Street-fighting RAG: chain-of-thought prompting (sgnt.ai)
		1 point by petesergeant on Jan 7, 2025 \| past