565 results for outer · 2.519s

News for “outer”
20 results • 2514 ms server time
Advertisement
Advertisement
Moozonian News
github.com• Mar 6, 2026• 1 min read
Show HN: Stateless Go GraphQL Federation Gateway, 1.58x Faster Than ApolloRouterI built a GraphQL Federation v2 gateway in pure Go.What's supportedAll core Federation v2 directives work out of the box:- @key — simple, composite, nested ("coord { lat lng }"), multiple @key per type, @key(resolvable: false) - @external — correct ownership filtering; stub references (e.g. a service that declares a type only to satisfy a key) are never mistaken for entity owners - @requires — chained dependency injection resolved in topological order - @provides — skips unnecessary _entities fetches when the parent service already covers all requested child fields - @shareable — prefers the parent subgraph to avoid extra entity fetches - @override — field ownership migration between subgraphs - @inaccessible — enforced at both schema composition and query validation - @interfaceObject — interface types as entities with inline fragment resolution - @composeDirective — custom directive preservation with consistency validation - @tag, @linkOperations: query and mutation. Independent subg
Advertisement
Moozonian News
image2image.ai• Nov 13, 2025• 1 min read
Show HN: I built a "router" for image to image AI models based on use caseHi HN, I'm the builder of image to image ai.Lately, I've been going deep down the rabbit hole of AI image models, and my main takeaway is: the landscape is incredibly fragmented and confusing for anyone who isn't living in this space 24/7.My frustration was that no single model is the best at everything.I found that nanobanana is fantastic for enhancing or merging multiple images, but it can't handle text editing. qwen is surprisingly good at in-image text manipulation, but its general enhancements are weaker. chatgpt is great for structured things like comics or infographics, and other models like kontext are strong generalists with fewer restrictions.This is a terrible experience for a normal user. Users don't care about which model to use. They have a task they want to accomplish, like "fix this text" or "make my headshot look professional."So, I built image2image.ai based on this premise.My project isn't another single model. It's a user-centric layer that sits on top of this fragm