Mutable.ai is automating corporations starting by automating software and software understanding. Our product auto wiki (https://wiki.mutable.ai/kubernetes/kubernetes, https://twitter.com/mutableai/status/1744426997575553413) turns code into wikipedia style articles with citations to the code is the best way to understand complex technologies
Omar is the founder of Mutable.ai. He was a researcher at DeepMind, publishing on Reinforcement Learning & GraphNets in NeurIPS. Omar was also part of a small team that developed a music recommender, which tied with Amazon Music in a live bake-off, and he has three patents in the recommender space. In a previous life, Omar was a theoretical physicist working on black holes and particle physics.
Mutable.ai is proud to introduce Auto Wiki, which lets you generate a Wiki-style website to document your codebase. Citations link to code, with clickable references to each line of code being discussed. Here are some examples of popular projects:
React: https://wiki.mutable.ai/facebook/react
Ollama: https://wiki.mutable.ai/jmorganca/ollama
Kubernetes: https://wiki.mutable.ai/kubernetes/kubernetes
D3: https://wiki.mutable.ai/d3/d3
Bitcoin: https://wiki.mutable.ai/bitcoin/bitcoin
Terraform: https://wiki.mutable.ai/bitcoin/bitcoin
Auto Wiki makes it easy to see at a high level what a codebase is doing and how the work is divided. In some cases, we’ve identified entire obsolete sections of codebases by seeing a section for code that was no longer important. Auto Wiki relies on our citations system which cuts back on hallucinations. The citations link to a precise reference or definition, meaning the wiki generation is grounded on the basis of the code being cited rather than free-form generation.