gabrielrecc

We ran a hackathon on scalable oversight with Gabriel Recchia as keynote speaker (watch the talk) and Ruiqi Zhong as co-judge. Here, we share the top projects and results. In summary: * We can automate the “sandwiching” paradigm from Cotra [1] by having a smaller model ask structured questions to elicit a true answer from a larger model and getting a response accuracy rate as output. * We can understand coordination abilities between humans and large language models quantitatively using asymmetric-information language games such as Codenames. * We can study scaling and prompt specificity phenomena in-depth using a simple framework. In this case, word reversal is investigated to evaluate the emergent abilities of language models. Watch the project presentations on YouTube. Thank you goes to the local organizers, Gabriel Recchia, Ruiqi Zhong and the wonderful hackathon participants from across the world. Automatic Sandwiching: Efficient Self-Evaluations of Conversation-Based Scalable Oversight Techniques By Sophia Pung and Gabriel Mukobi Abstract: Our project furthers the progress of Scale Oversight through automation of the sandwiching paradigm. In the Bowman et al. (2022) paper, the question is presented of how humans can effectively prompt unreliable, superhuman AIs to answer questions via conversation to arrive at accurate answers. We want to explore and evaluate the methods that humans can use reliably to elicit honest responses, from a more intelligent AI. We present a novel method, called Automatic Sandwiching, for implementing this paradigm. We implement a simplified version of this, evaluate our system on 163 training examples from Multi-task Language Understanding (MMLU) with 2 different oversight techniques. We provide code to reproduce our results at sophia-pung/ScaleOversight. They replicate a non-expert human overseer by taking a smaller model (text-curie-001) and providing it specific instructions to get non-deceptive answers in a question and