I let an AI agent do architecture research on my GPT repo

This page cannot be shown here. You can still read it on the original site — the toolbar below keeps your place in the directory.

For the past two weeks, an AI agent ran autonomous architecture research on BlaGPT , my GPT-2-scale playground for testing LLM techniques. It ran about 100 short proxy experiments and 22 full training runs, implemented techniques from papers, kept its own ledger, and pushed everything to the repo. Validation loss went from 3.2354 to 3.1965. The agent is Keche, my personal AI assistant that lives…

Read on /2026/07/16/i-let-an-ai-agent-do-architecture-research-on-my-gpt-repo ↗