I don't think OP is looking for context from the AI model perspective but rather a process for maintaining a mental picture of the system architecture and managing complexity.

I'm not sure I've seen any good vendors but I remember seeing a reverse devops tool posted a few days ago that would reverse engineer your VMs into Ansible code. If that got extended to your entire environment, that would almost be an auto documenting process.

Context rots when it stays implicit. Make the system model an explicit artifact with fixed inputs and checkpoints, then update it on purpose. Otherwise you keep rebuilding the same picture from scratch.

Im honestly looking for both. I haven't found a vender to do this well for just humans nor am I seeing something that can expose this context, read only, to all of the ai agent coding models

I will check that tool out.

I'm seeing a lot of duplication in our AI coded repos that is getting to the point of being problematic to maintain.

history doesn't repeat but it definitely rhymes

part of the value add of owning both the model and the tooling

Jetbrains is trying but I feel like they're very very behind in the space

Looking at you Deepmind and OpenAI

Google sponsors the python foundation as per this page: https://www.python.org/psf/sponsors/

Kinda crazy that the top level "Visionary Sponsor" is a donation level of $160k. There's also 0 sponsors at the $100k level. I was also surprised to see Netflix at $5k and Jane Street at $17k. Maybe they should give more but there's a lot of names absent and that says more

written by a company whose product is basically selling expert advice via training data review

> Raw intelligence meets battle-tested experience

>A global community of the smartest people in every field who've shipped products, won cases, published breakthroughs, and made decisions under pressure.

For them the price of the 125 GBP tab is nothing compared to 6-7 figure investment they're about to make based on your advice.

Reminder that it's in the lecun's interests to talk up AMI and to explain why they're going to win when they didn't do so at FAIR.

Yann joins Ilya, Karpathy, Sutton + Carmack when he says LLMs are a dead end, though.

Karpathy is probably the most careful not to write off LLMs entirely but he seems pretty skeptical.

a lot of the third party tools follow the time honored tradition of duplicating an internal service at a leading engineering org (FAANG) and then making it available as a SAAS product