Archon: An Architecture Search Framework for Inference-Time Techniques — mentioned by m_ke

Mon, 16 Dec 2024 15:27:28 GMT

Sorry I wasn't clear enough, the cheap to validate part is only needed to train a large base model that can handle writing individual functions / fix bugs. Planning a whole project, breaking it down into steps and executing each one is not something that current LLMs struggle at. Here's a recipe for a human level LLM software engineer: 1. Pretrain an LLM on as much code and text as you can (done already) 2. Fine tune it on synthetic code specific tasks like: (a) given a function, hide the body, make the model implement it and validate that it's functionally equivalent to the target function…

Paper and discussion history. A mention is not an endorsement.

Archon: An Architecture Search Framework for Inference-Time Techniques · HackerPapers discussions

Archon: An Architecture Search Framework for Inference-Time Techniques — mentioned by m_ke