AIS Mirror Research Repository

Advertisement

Latest Research Feed

Constitutional AI: Harmlessness from AI Feedback

arXiv:2212.08073 • Anthropic • Dec 15, 2022

We train a non-evasive and harmless AI assistant using constitutional AI, a method for training a harmless AI assistant without human labels.

The Mirroring Effect in Large Language Models

AIS Research • Oct 12, 2023

Analysis of how LLMs reflect user bias in long-context windows and the implications for alignment strategies.

GPT-4 Technical Report

OpenAI • Mar 14, 2023

We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs.

Sparks of Artificial General Intelligence: Early experiments with GPT-4

arXiv:2303.12712 • Microsoft Research • Mar 22, 2023

We contend that GPT-4 is part of a new cohort of LLMs (along with ChatGPT and Google's PaLM) that exhibit more general intelligence than previous AI models.

Stochastic Parrot Archive

foundational papers on the limitations of LLMs as probabilistic pattern matchers.

Access Vault →

Alignment & Ethics

Key readings on AI safety, alignment theory, and ethical deployment frameworks.

Access Vault →

Open Source Models

Repository of weights, benchmarks, and fine-tuning guides for Llama, Mistral, and Falcon.

Access Vault →

Support the Mirror Archive

Independent research relies on community support. Direct funding ensures continued fidelity.

Recommended Tools