XIO

xWire

Posts from every feed QUEST has found across the web — blogs, news, podcasts, channels and more.

HN's home page

Show HN: EchoChain to see what happens when LLMs play telephone

Hey HN Community!I created `echoChain` to explore the following phenomenon: how much data retained after LLMs exchange responses multiple times?Imagine the game of telephone but with AIs. Each model converts the response into a question, which is then answered. After several rounds, facts get mutated, details get stripped, and the answer is far removed from the initial one.`echoChain` is an OSS Python CLI that helps measure this process. It allows for multi-model testing, model rotation,…

Show HN: Coding agent spots your AI practices and the ones you're missing

Frontier models improve at a pace faster than the pace at which most humans are able to keep up. Not all of us are obsessed with pushing the boundaries of our agents and trying new ways to work with them. I often spend 12+ hours a day working with an LLM, and still, when I talk to people, I hear of ways of working I hadn’t thought of.What if we could speed up that pace of learning? What if everybody shared their practices of how they are making the most of AI, and if we could learn from each…