Tag
@tobi reports good results using a local Qwen 3.6 26b model for autoresearch with a 'vibed pi advisor' extension that periodically consults GPT 5.5 for ideas, suggesting this direction has merit.
EvolveMem introduces a self-evolving memory architecture for LLM agents that optimizes retrieval configurations through LLM-powered diagnosis and iterative research cycles, achieving significant performance improvements on benchmarks like LoCoMo and MemBench.
Andrej Karpathy released autoresearch and the open-source community rapidly created over 40 forks and ports, including an Apple Silicon macOS version.
Developer Ivan Fioravanti demonstrates running Andrej Karpathy's autoresearch project locally with a 6-bit quantized Gemma-4-26B model on Apple Silicon, suggesting successful training of Gemma 4 E2B IT variant.
Andrej Karpathy's autoresearch pattern highlights how current AI agents run experiments in isolation, wasting compute by duplicating work and rediscovering dead ends.