MIT beats AGI-PUB benchmark record by 20% with new LLM
A team from MIT has made significant progress in abstract task solving using an 8 billion parameter Language Model (LLM) and an innovative technique called Test-Time Training (TTT). With a performance of 61.9% on the ARC-AGI-PUB benchmark, they significantly outperformed… Read More »MIT beats AGI-PUB benchmark record by 20% with new LLM