Viewing profile — IxInfra

I've found that this works for smaller projects but starts breaking down when you're dealing with large-scale codebases or systems that change frequently.

Let us know if you have any feedback. We welcome contributors and are working every day to improve based on what our users want. GitHub = https://github.com/ix-infrastructure/Ix Op…

Stop playing 20 questions with your AI every session. Every time you start a new session your agent has no idea what system it's working in. Not just losing conversation history, l…

every session is a constant repeat of re-explaining the same architecture, service boundaries, etc. wondering how others are dealing with this?

https://github.com/ix-infrastructure/Ix sorry heres the link.

2 approaches are emerging for giving ai agents structural understanding of a codebase. 1. LLM inferred. fast to build. but edges are labeled INFERRED because the model is just gues…

Thank you for your answer.

it was a genuine question...

Interesting. Where are you getting the hooks, prompts, and skills sourced from? Are these custom-built or pulled from an existing framework?

This is really interesting, especially the chunking and parallel Haiku approach. Curious how it holds up as note volume grows. At some point you're still doing N relevance checks p…

[dead]

[dead]

[dead]

the distribution muscle being a separate skill is so underrated. most technical founders assume if you build something good it finds its own audience. it almost never does. sounds …

the duct tape framing is fair but the deeper issue is the model has no persistent understanding of the system it's working in. each generation starts from scratch with no memory of…

Hey HN, I'm Tanner, one of the founders of Ix. Every time we started a new AI session, the agent had no idea what system it was working in. Not just losing conversation, losing the…

The 0.92 semantic similarity threshold is interesting. curious how you landed on that number? Thinking too low and you risk false cache hits but too high and you lose most of the s…